writing high quality scientific research papers using chatgpt

Home → Academic Writing → How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

Jordan Kruszynski

• January 4, 2024

If you’re an academic, you’ve probably spent a lot of time planning and writing research papers. It’s a fine art, and one that requires a fair amount of skill, precision and preparation. But whether you’re an old master in the field, or a rookie embarking on your first serious research paper, there are tools that can help you to simplify the planning stages and organise your thoughts more effectively.

One of those tools is the (in)famous ChatGPT , and it’s this that we’ll be focusing on in our article. In the right hands, ChatGPT can become a powerful research tool that will make your paper-writing that little bit easier. So sit back, relax, and discover our tips and tricks for using ChatGPT to write a research paper.

What is ChatGPT?

Just in case you don’t already know, ChatGPT is an artificial intelligence tool developed by OpenAI that can help you with your research. It uses natural language processing to understand what you’re looking for and provide you with relevant information. You can ask it questions, and it will provide you with answers in a conversational style, as well as offer sources to back up its information.

One of the biggest advantages of ChatGPT is that it can save you time. Instead of spending hours searching for sources, you can simply ask ChatGPT for help. This can bring you a reliable list of sources for further investigation fairly quickly. It’s crucial to note however that the AI shouldn’t be exploited to do the actual writing of the paper for you. This could see you accused of plagiarism or misconduct, and besides, as a researcher, you’re probably rightfully proud of your ability to write a compelling paper.

Another advantage of ChatGPT is that it’s always available (even when libraries or other sources of information might be inaccessible) so you can work on your research paper at any time of day or night.

Interested in learning more about how AI programs like ChatGPT are changing the academic landscape? Listen to Oxford researcher Samantha-Kaye Johnston’s views from the frontline in this exciting episode of The Research Beat podcast.

The benefits of using ChatGPT to write a research paper

There are many benefits to using ChatGPT for research papers. Firstly, as we mentioned earlier, it can save you time . A slow drag of several hours looking for specific sources can be reduced to just a few minutes with the AI’s help.

Secondly, it can help you find sources that you might not have found otherwise . ChatGPT has access to a wide range of sources, including academic journals and books.

Thirdly, it can help you organise your research . ChatGPT can provide you with a summary of the information you’ve gathered, making it easier to analyse and integrate into your research paper.

How to use ChatGPT to write a research paper – a step by step guide

• Start by creating a list of questions that you want to answer in your research paper.
• Open ChatGPT and ask it one of the questions on your list, for example, ‘What is the critical history of feminist literature in Europe?’
• ChatGPT will provide you with a list of sources to check out.
• Read through the sources and take notes on the information that is relevant to your research question.
• Repeat steps 2-4 for each question on your list.
• Once you’ve gathered all of your information, organise it into an outline for your research paper.
• Use the information you’ve gathered to write your research paper.

Working with your sources

Once you have your sources in order, you might want to use prompts to get help from ChatGPT with other parts of the writing process. A prompt is a specific instruction to the AI that can give you tailored information or responses. For example, if you’re struggling to understand part of another research paper, you could use the following prompt:

‘Please explain the following paragraphs in simple words. I am having trouble understanding (insert concept here).’

Input the prompt along with the relevant passage from the source, and ChatGPT will provide a summary that could help you to unlock your understanding of the tricky concept.

Looking for ChatGPT prompts tailor-made for academics? Check out Audemic’s list of over 50 prompts to help you with your work and research!

Writing tips and tricks for using ChatGPT

When using ChatGPT to write a research paper, it’s important to keep a few things in mind. Firstly, make sure that you’re using reliable sources . ChatGPT can provide you with a list of sources, but it’s up to you to determine which ones are reliable.

Secondly, make sure that you’re paraphrasing the information you’ve gathered in your own words . You don’t want to cheat or be accused of it.

Finally, make sure that you’re using the information you’ve gathered to answer your research questions . Everything you uncover through ChatGPT should be used to feed your own understanding and improve the quality and precision of your answers.

Common mistakes to avoid when using ChatGPT to write a research paper

While ChatGPT is an excellent tool for research papers, there are some common mistakes to avoid:

• Crucially, don’t rely too heavily on ChatGPT. It’s essential to do some of your research on your own and use ChatGPT to supplement it.
• Don’t forget to cite your sources correctly. Just because ChatGPT provided you with the information doesn’t mean that you don’t need to cite it. Moreover, ChatGPT cannot actually produce academic citations for you.
• Always remember to proofread your research paper carefully, especially if you’ve used AI elements to construct it.

ChatGPT vs. traditional research methods

While traditional research methods have their advantages and always will, ChatGPT, as we’ve seen, has some of its own. We think one of the best uses for AI programs like ChatGPT is to accelerate parts of the paper-writing process that would otherwise take hours. If you can use the AI to produce a list of interesting and relevant sources, then you can get to work quickly as an academic, studying and analysing those sources to determine their value within your paper. In general, if you approach ChatGPT with an attitude of maintaining quality and integrity, then it can only enhance your work.

Final Thoughts

ChatGPT is everywhere at the moment, and while it has stirred up a great deal of controversy thanks to its implications for academic integrity, it can be an excellent tool for helping to write research papers . The key is using it correctly, and not relying too heavily on it. Focusing on how it can enhance your already-sharp academic writing skills will allow you to save time, find plenty of valuable sources, and organise your paper’s structure more effectively. And that’s how to use ChatGPT to write a research paper!

ChatGPT is not the only AI tool that can help with these parts of the paper-writing puzzle. If you want to listen to academic papers, break them down into digestible pieces and freely take notes on them, then Audemic is waiting for you. Try it for free today!

Keep striving, researchers! ✨

Table of Contents

Related articles.

How to Publish a Research Paper: A Step-by-Step Guide

You’re in academia. You’re going steady. Your research is going well and you begin to wonder: ‘How exactly do I get a

Behind the Scenes: What Does a Research Assistant Do?

Have you ever wondered what goes on behind the scenes in a research lab? Does it involve acting out the whims of

How to Write a Research Paper Introduction: Hook, Line, and Sinker

Want to know how to write a research paper introduction that dazzles? Struggling to hook your reader in with your opening sentences?

Blog Podcast

Privacy policy Terms of service

Subscribe to our newsletter!

Discover more from Audemic: Access any academic research via audio

Subscribe now to keep reading and get access to the full archive.

Type your email…

Continue reading

How to Use ChatGPT in Scientific Writing: Tips and Tricks

Updated December 11th, 2023

In this article, we want to adress a very current but controversial topic: The use of artificial intelligence (AI) language models such as ChatGPT in scientific writing . There are several ways you can utilize ChatGPT while you are doing research or while you are writing a scientific manuscript. In this article we will cover several possibilities on how to use ChatGPT in scientific writing. Please also read how to write a scientific paper before you ask ChatGPT anything about it.

Disclaimer : As an advanced AI model capable of understanding and generating natural language, ChatGPT can help you in multiple ways. But although the title of this article is “How to use ChatGPT in Scientific Writing”, be aware of the following:

Do not use ChatGPT to write actual text for your scientific manuscript!

ChatGPT may generate wrong and plagiarized content. Although you can check the output of ChatGPT with tools such as PlagiaShield , you should always be extra careful when copying any parts. Otherwise, you might get your research rejected instantly .

What to Consider Before ChatGPT Can Help You in Scientific Writing

First of all, it is important how you perceive ChatGPT .

It is by no means an automatic typewriter that generates text to be copied and pasted into your manuscript, presentation or other scientific documents. Rather, I suggest that you think of ChatGPT as an assistant that can help you with many things. However, it also has some limitations that you should be aware of before implementing ChatGPT into any of your workflows. In science, ChatGPT may only be of use, if the user (you) has substantial knowledge and experience in her/his field. You need to be able to differenciate meaninful from useless and more important right from wrong information.

It is tempting to give ChatGPT a prompt such as “write me an introduction for a scientific paper with the following title: ‘XYZ'”. I can only recommend everyone to try it – once! The result will make some sense and there might be some valuable information in it but it will most likely not suit your specific topic or thesis. The potential of ChatGPT lies in somewhat more sophisticated approaches.

The Top 6 Applications for ChatGPT in Scientific Writing

Let’s now dive into specific areas and explore how to use ChatGPT for scientific writing. Here we will briefly go through the 5 best ways to use ChatGPT while doing research or writing a scientific manuscript. Each point will be discussed in detail below with example prompts.

• Brainstorming and Finding Arguments
• Summarizing and Concentrating
• Paraphrasing and Simplifying
• Identifying Key Words and Key Points
• Creating Figures and Graphs
• Find Alternative Phrases and Synonyms

But now let us go into details so you can learn how ChatGPT can help you with your scientific research.

1. Brainstorming and Finding Arguments

ChatGPT is a great tool to help with generating ideas, finding arguments and general brainstorming. This can be helpful either before you start collecting information or after you already gathered some data in order to check if you maybe missed a relevant point.

How to Brainstorm in Scientific Writing Using ChatGPT

For example, you can ask ChatGPT: “ Give me treatment options for hepatocellular carcinoma. Use bullet points .”

It will give you an output that will look something like this:

ChatGPT : Sure, here are the treatment options for hepatocellular carcinoma in bullet points:

• Surgery (resection or liver transplant)
• Radiofrequency ablation (heat to destroy cancer cells)
• Transarterial chemoembolization (TACE) (chemotherapy drugs injected directly into tumor)
• Systemic chemotherapy (drugs given through the bloodstream)
• Targeted therapy (drugs that target specific proteins or pathways involved in cancer growth)
• Immunotherapy (drugs that help the immune system to fight cancer)
• Radiation therapy (high-energy radiation used to kill cancer cells)
• Palliative care (treatment to relieve symptoms and improve quality of life)

At first sight, this list seems quite complete but depending on your level of expertise you might find that there are things missing (what about radioembolization, microwave ablation etc.). Maybe there will even be obvious mistakes. This is especially important in fields with rapid developments or novel innovations. As ChatGPT has no access to very current data, you need to be able to identify mistakes or gaps in its output .

However, lets say you already made your list and discussed treatment options for hepatocellular carcinoma but somehow missed to include transarterial chemoembolization . In this case, ChatGPT will make you aware of this gap and will allow you to make your text or list more comprehensive. Again, please always be critical about the output and do additional scientiftific research by yourself to fact-check if you are not entirely sure about some things.

How to Use ChatGPT to Compare Things and Find Arguments in Scientific Writing

Given the huge data set that ChatGPT is trained on, it knows a lot about a lot of things. Therefore, you can use it to compare things and find arguments for different items.

For example, you could ask ChatGPT: “ Compare radiofrequency and microwave ablation for the treatment of hepatocellular carcinoma “.

In this case, my test output looked like this:

ChatGPT : Radiofrequency ablation (RFA) and microwave ablation (MWA) are two minimally invasive procedures used to treat hepatocellular carcinoma (HCC). Both techniques aim to destroy cancerous tissue using thermal energy. However, there are some differences between the two methods:

• Mechanism of action: RFA uses high-frequency electrical currents to generate heat, while MWA uses electromagnetic waves to generate heat. MWA can achieve higher temperatures in a shorter amount of time.
• Tumor size: RFA is generally more effective for smaller tumors, typically those less than 3 cm in size. MWA may be better for larger tumors, as it can create a larger ablation zone.
• Procedural time: RFA requires a longer procedural time than MWA. MWA can complete treatment in a shorter time.
• Complications: Both RFA and MWA are generally safe and have few complications. However, there is a slightly higher risk of thermal injury to nearby tissues with MWA.
• Cost: MWA is generally more expensive than RFA.

In summary, RFA and MWA are both effective treatment options for HCC, but the choice between the two may depend on the tumor size and location, as well as the patient’s individual situation and the availability of the techniques in the treatment center.

Again, you need specific knowledge to evaluate this information with regard to the correctness. However, you will get some information of points, where you can get into more detail. For example, maybe you did not include potential differences in procedural time in your discussion. You now can research this point regarding real and authorized information and then add this to your discussion citing the respective references.

Helpful ressources to perform scientific literature research are PubMed and GoogleScholar (among many others).

2. Summarizing and Concentrating

ChatGPT is great in summarizing and modifying text. You can copy and paste any text into the search field and tell it to summarize it into one paragraph or even into single sentences. Or you can even tell it to summarize prior studies for you. Again, there are some things to know beforehand and you are asked to critically evaluate the output.

How to Use ChatGPT for Summarizing Scientific Texts

For example, you can give ChatGPT a scientific text as input. In this test case, I put the first section of the Wikipedia Article of Hepatocellular Carcinoma in the text box and told it to summarize it using just 3 sentences. “ TEXT. Summarize this. Three sentences .”

Using this prompt, I received the following output:

ChatGPT : Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and is linked to chronic liver injury and inflammation, often caused by chronic viral hepatitis infection or exposure to toxins. HCC has a poor prognosis and treatment varies depending on the specifics of the tumor and overall health of the patient. The incidence of HCC is highest in Asia and sub-Saharan Africa where hepatitis B infection is endemic, but it is also increasing in the United States and other developing countries due to an increase in hepatitis C virus infections.

Again, there might and will be mistakes but this can be a helpful tool to get a short and concise summary of a scientific text or study beyond what is written in the abstract . For example, you can also try to put the DOI/link and title of a study as input. Please be aware, that this will not work for every link, especially if the study is more recent.

Furthermore, make sure that there are no one-to-one copies. If you want to use the output, perform a plagiarism check using tools such as PlagiaShield .

How to Use ChatGPT to Concentrate Text in Scientific Writing

Almost everybody, that has published anything in the scientific world or even has presented on a scientific congress has faced ‘ word limits ‘. Maybe it is the abstract, that can only have 200 words – but your study is soo extensive. Or you want to submit your paper to a journal, that has a word limit of 2400 for the manuscript body – but your manuscript has 3500…

The approach is similar to the one above but now you need to tell ChatGPT that you want to reduce the text to a specific length or “by 10%” . Although this can work quite well, it will sometimes ignore your specifications and write the output significantly longer or shorter.

Furthermore, this approach can have some privacy issues . You can´t know, how the data you put into the text field is collected and processed. I strongly advise not to put sensitive or protected data into the chat box.

3. Paraphrasing and Simplifying

Although summarizing and concentrating text will also result in rephrasing sentences, you can use ChatGPT to adjust the complexity or tone of a text . Maybe you have written a scientific article but you now want to make a presentation for a broader audience. In this case, you might want to reduce scientific terms and implement an easier language.

Lets say you have the following definition for hepatocellular carcinoma:

Hepatocellular carcinoma (HCC) is a neoplastic proliferative disorder of the liver characterized by the malignant transformation and aberrant growth of hepatocytes, which are the primary functional cells of the liver parenchyma, leading to the development of a tumor with the potential for local infiltration, regional metastasis, and systemic dissemination, resulting in significant morbidity and mortality. This pathological condition is thought to arise from a complex interplay of genetic and environmental factors, including but not limited to chronic viral hepatitis, alcohol abuse, non-alcoholic fatty liver disease, and exposure to hepatotoxic agents, which promote the accumulation of genetic mutations, epigenetic alterations, and chromosomal instability within the hepatocyte population, ultimately leading to the dysregulation of multiple signaling pathways involved in cell growth, survival, and differentiation.

You can tell ChatGPT to take the text above as input and “ re-write it using shorter sentences and simpler language “. In this case, I got the following output:

ChatGPT : Hepatocellular carcinoma (HCC) is a type of liver cancer that happens when liver cells grow out of control and form a tumor. This can cause serious health problems and can even be deadly.

Several things can increase the risk of getting HCC, including chronic viral hepatitis, alcohol abuse, and exposure to harmful chemicals. These things can damage the liver and make it more likely for cancer to develop.

This can be especially useful for scientific communications that need to be suitable for a broader audience. I cannot emphasize this enough, please read the output carefully and use it only for orientation and content input.

4. Identifying Key Words and Key Points

Another helpful application can be the identification of key words and key points for your study. Lets talk about how to use ChatGPT to identify key words and key points in scientific writing:

Many scientific jounals require you to provide key words in addition to the abstract. Furthermore, key points can be helpful to communicate your key findings and they might also be required by some journals .

Lets say, you wrote a manuscript for the following study: “ In-patient care trends in peripheral artery disease in the German healthcare system over the past decade “

You already wrote your manuscript but now you also need some key words and key points. In this case, the journal also requires your key words to be compatible with the MeSH (Medical Subject Headings) database.

Example on How to Use ChatGPT for Generating MeSH Key Words

You could paste your abstract to ChatGPT as input and ask something like this: “ I have this abstract: [paste abstract ]. Please give me 5 key words and 3 key points. Make the key words MeSH compatible. “

Here I got this output:

ChatGPT : Sure, here are five potential keywords that are compatible with the PubMed MeSH (Medical Subject Headings) database:

• Peripheral Arterial Disease
• Hospitalization/trends
• Comorbidity
• Revascularization
• Health Care Costs

Please note that these MeSH terms may have subheadings that can be used to refine the search further. Additionally, there may be other MeSH terms that are relevant to your study that are not included in this list.

Here are three potential key points for your study:

• Hospitalizations due to peripheral artery disease have increased over the past decade, with a notable rise in comorbid patients.
• The average cost per hospitalization has increased over time, reflecting the growing burden of peripheral artery disease on healthcare systems.
• Endovascular approaches, such as percutaneous transluminal angioplasty, are becoming more common for treating peripheral artery disease, particularly in smaller vessels below the knee.

As you are the expert of your study , you might find some key words more suitable and some key points not fitting. However, this approach can be a good start and facilitate your progress in scientific writing.

5. Creating Figures and Graphs

ChatGPT can be a good ressource and assistance during the generation of figures and graphs for your scientific study. In this paragraph we want to talk about how to use ChatGPT to create figures and graphs in scientific writing. Starting from getting ideas to the actual generation of figures, there are several steps where you can utilize ChatGPT.

How to Use ChatGPT to Get Ideas for Graphs in Scientific Writing

Let´s start with which graphs to use. If you have enough information for your study, you can ask ChatGPT for ideas for graphs. For example, given the information (abstract) of the prompt before, you could ask: “ What would be great graphs for the study mentioned above? “

ChatGPT: Based on the information provided in the abstract, here are a few graphs that could be useful for this study:

• Line graph showing trends in the number of hospitalizations for peripheral artery disease over time (2009-2018). This graph could highlight the increase in hospitalizations over the decade.
• Bar graph comparing the frequency of different comorbidities among patients hospitalized for peripheral artery disease. This graph could help identify the most common comorbidities associated with the disease.
• Stacked bar graph comparing the frequency of different revascularization procedures performed for peripheral artery disease, such as percutaneous transluminal angioplasty, bypasses, and endarterectomies. This graph could show the shift from surgical to endovascular approaches over the decade.
• Scatter plot showing the relationship between hospitalization costs and patient comorbidities or severity of peripheral artery disease. This graph could help identify factors that contribute to higher hospitalization costs.
• Box plot showing the distribution of the linear van Walraven score among patients hospitalized for peripheral artery disease over time. This graph could highlight the increasing severity of cases over the decade.

These are just a few ideas for potential graphs based on the information provided in the abstract. The most appropriate types of graphs may depend on the specific research questions and data available for the study.

You will probably already have some ideas that you want to illustrate in your paper, but using this prompt will give you some concrete suggestions in no time. Since we tend to use similar approaches (and similar numbers) in our studies, this can also be a good source of new ideas to help broaden your horizons.

How to Use ChatGPT to Create Graphs in Scientific Writing

If you have ever written a scientific paper, you have probably been at the point where you wanted to illustrate your data with a graph or plot . There are several options and software out there to create high quality graphs and this will not be a step-by-step guide on how to use different software. From Excel to SPSS to Python ( Matplotlib ) and R ( ggplot2 ), many tools can be used and will most likely produce acceptable graphs. However, both Matplotlib (Python) and gglplot2 (R) are very powerful and able to generate excellent and extremely versatile visualizations of your data . The downside is that you now have to learn how to program in those languages.

Now what does that have to do with ChatGPT you might ask? If you ever worked with Python or R, you will have come to the point where you wanted or needed to tweak your plot in some way. To do this, you read through guides, forum posts and stack overflow and ultimately found the line of code that did just what you wanted.

However, you may have never used Python or R before and feel overwhelmed by the thought of learning a programming language just to create some plots. Whether you are a beginner of this approach or you already found yourself struggeling while trying to adjust some of your figures, ChatGPT is here to help.

Example on How To Use ChatGPT to Create a Scientific Graph

As a novice, you can ask ChatGPT on how to generate a graph in any programming language . For example:

“ How to generate a scatter plot in R using ggplot2? “

In this case, you will get specific instructions with annotations and even readily written code to use to generate your high-quality figure.

Naturally, you need some knowledge on how to install and use R. However, with just basic knowledge you can kickstart the creation of your first high-end scientific graphs. And be aware that you can just ask for any modification .

Maybe you want to add a regression line to your plot: “ How to add a regression line to this graph? “

The detailed descriptions in the output of ChatGPT will help you to modify your code yourself. Before you know it, you will be able to create beautiful and expressive plots on your own , and you will use ChatGPT for more advanced questions.

Of course, you will need to learn how to import your data, install packages, manage data frames, and much more. But with the help of ChatGPT, the learning curve of any programming language can be significantly flattened enabling everybody to create lovely scientific graphs and plots. If you want to learn more about data visualization with generative AI, I can reccomend the following online course on data visualization with ChatGPT *:

6. Alternative Phrases and Synonyms

If you´re writing about a certain topic, you may find yourself using the same phrases over and over again. Not only does this create a somewhat monotonous aspect, but it also limits how your manuscript can be perceived. For example, if you´re always using the term “patients with oncologic diseases” in your paper that analyzes something about oncology patients, you are missing something out. Same thing is true if you´re writing a rebuttal letter and you start your comments to the reviewers always the same way.

Try asking ChatGPT for alternative phrases or synonyms. This will not only spice up your text, but also broaden your horizons for future scientific writing.

Just paste your overused phrase into ChatGPT and ask for (lets say 5) alternative phrases or synonyms. In no time you will have a good basis to use in your manuscript.

Happy writing!

Some links on this site are affiliate links (*). If you choose to buy a product using these links, I might get a commision for this purchase. For you, this does not change the price.

Board-certified radiologist, blogger, tech enthusiast, and clinician scientist working in Germany.

View all posts

Share this:

Discover more from rad insights.

Subscribe now to keep reading and get access to the full archive.

Type your email…

Continue reading

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Innovation (Camb)
• v.4(6); 2023 Nov 13
• PMC10654578

ChatGPT for scientific paper writing—promises and perils

1 Innovation Research Institute of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China

2 Shanghai Key Laboratory of Gynecologic Oncology, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China

Jian-ping Zuo

3 Laboratory of Immunopharmacology, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China

The use of artificial intelligence (AI) in academic paper writing is witnessing a surge in popularity. Specifically, ChatGPT, a member of the generative pre-trained transformer (GPT) family of large language models (LLMs), has found application across diverse scientific and medical domains, encompassing detection of drug interactions, drug safety monitoring, medical image analysis, and the refinement of research papers. 1

Concerns and ethical considerations

Through the use of sophisticated algorithms and data analysis capabilities, ChatGPT plays a pivotal role in expediting the scientific writing process for researchers. This assistance is particularly valuable, as researchers often grapple with time constraints during the composition of scientific papers, a task known for its inherent lengthiness. ChatGPT assists researchers by aiding in the organization of pertinent material, data gathering and analysis, organizing the relevant material, gathering and analyzing data, suggesting titles, outlining data analysis methods and results, drawing conclusions from the detailed results, generating the initial draft of a scientific paper, and proofreading the final version. 2 Furthermore, ChatGPT proves invaluable for non-native speakers of the academic language, who may encounter difficulties in crafting scientific manuscripts.

Ethical considerations

Although ChatGPT offers undeniable advantages in scientific paper writing, several concerns have emerged. One worry is that it may facilitate plagiarism if researchers abuse the software to produce complete essays without putting in any effort. One notable apprehension is its potential to facilitate plagiarism if unscrupulous researchers misuse the software to effortlessly produce complete essays. The emergence of AI-generated texts presents a novel and intriguing development; however, it is fraught with unresolved issues from both legal and ethical standpoints.

Fostering dependency on AI

Research by Faisal et al. 3 has demonstrated that ChatGPT may produce erroneous or misleading interpretations in scientific writing. Fabricating or falsifying research becomes a disturbingly simple endeavor, especially in critical fields such as medicine, in which treatment decisions directly affect patients’ well-being. Consequently, researchers using ChatGPT must exercise caution and demonstrate a profound understanding of its multifaceted manifold components to uphold ethical standards. Another potential drawback lies in the possibility that ChatGPT could discourage originality in writing by fostering excessive dependence. Overreliance on ChatGPT for generating ideas may diminish researchers’ capacity to formulate unique thoughts and perspectives, ultimately leading to a stagnant writing style bereft of creativity and originality ( Figure 1 ).

ChatGPT: A double-edged sword for scientific writing

Inspired by the classic tale “Journey to the West,” this illustration metaphorically represents the dual nature of using ChatGPT in scientific research paper writing. Like Tang Monk’s control over Sun Wukong through the “tightening-crown spell,” researchers harness ChatGPT’s potential to enhance their scientific writing capabilities. However, the improper use of ChatGPT may restrict the development of their original expression, even potentially leading to misleading interpretations and erroneous outcomes.

Challenges in detection and authorship

Moreover, as previously reported, 4 academic reviewers presented with abstracts generated by ChatGPT were able to identify only 63% of the fraudulent ones. Furthermore, authorship involves being liable for the work, which is a key point with which LLMs cannot comply effectively. As a result, extant authorship guidelines, prevalent in all Springer Nature journals 5 and the Elsevier journals (see https://www.elsevier.com/about/policies/publishing-ethics ), unequivocally stipulate that LLMs such as ChatGPT should not be acknowledged as co-authors.

Embracing the benefits of ChatGPT

Notwithstanding the potential drawbacks and risks associated with ChatGPT in academic paper writing, its benefits are both substantial and undeniable. ChatGPT can enable novel and creative approaches to academic paper writing, by facilitating constructive feedback, guidance, and resources. ChatGPT can also enhance efficiency and effectiveness, by streamlining some of the mundane and laborious tasks of writing, such as formatting, referencing, and proofreading ( Figure 1 ). The incorporation of ChatGPT into academic paper writing processes holds the potential to elevate the quality and productivity of research endeavors, yielding superior outcomes.

In sum, ChatGPT is a technological tool with the potential to yield both positive and negative outcomes contingent upon its prudent and judicious application. Although it has the potential to be a valuable asset for scientific writing, it is incapable of supplanting human writing and critical thinking skills. Therefore, any use of AI in academic writing must adhere steadfastly to the principles of honesty, rigor, and originality.

Acknowledgments

This work is supported by the National Natural Science Foundation of China (grants 82374108 and 82004004) and the Shanghai Municipal Science and Technology Major Project.

Declaration of interests

The authors declare no competing interests.

Published Online: October 17, 2023

AI-assisted writing is quietly booming in academic journals. Here’s why that’s OK

Lecturer in Bioethics, Monash University & Honorary fellow, Melbourne Law School, Monash University

Disclosure statement

Julian Koplin does not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and has disclosed no relevant affiliations beyond their academic appointment.

Monash University provides funding as a founding partner of The Conversation AU.

View all partners

If you search Google Scholar for the phrase “ as an AI language model ”, you’ll find plenty of AI research literature and also some rather suspicious results. For example, one paper on agricultural technology says:

As an AI language model, I don’t have direct access to current research articles or studies. However, I can provide you with an overview of some recent trends and advancements …

Obvious gaffes like this aren’t the only signs that researchers are increasingly turning to generative AI tools when writing up their research. A recent study examined the frequency of certain words in academic writing (such as “commendable”, “meticulously” and “intricate”), and found they became far more common after the launch of ChatGPT – so much so that 1% of all journal articles published in 2023 may have contained AI-generated text.

(Why do AI models overuse these words? There is speculation it’s because they are more common in English as spoken in Nigeria, where key elements of model training often occur.)

The aforementioned study also looks at preliminary data from 2024, which indicates that AI writing assistance is only becoming more common. Is this a crisis for modern scholarship, or a boon for academic productivity?

Who should take credit for AI writing?

Many people are worried by the use of AI in academic papers. Indeed, the practice has been described as “ contaminating ” scholarly literature.

Some argue that using AI output amounts to plagiarism. If your ideas are copy-pasted from ChatGPT, it is questionable whether you really deserve credit for them.

But there are important differences between “plagiarising” text authored by humans and text authored by AI. Those who plagiarise humans’ work receive credit for ideas that ought to have gone to the original author.

By contrast, it is debatable whether AI systems like ChatGPT can have ideas, let alone deserve credit for them. An AI tool is more like your phone’s autocomplete function than a human researcher.

The question of bias

Another worry is that AI outputs might be biased in ways that could seep into the scholarly record. Infamously, older language models tended to portray people who are female, black and/or gay in distinctly unflattering ways, compared with people who are male, white and/or straight.

This kind of bias is less pronounced in the current version of ChatGPT.

However, other studies have found a different kind of bias in ChatGPT and other large language models : a tendency to reflect a left-liberal political ideology.

Any such bias could subtly distort scholarly writing produced using these tools.

The hallucination problem

The most serious worry relates to a well-known limitation of generative AI systems: that they often make serious mistakes.

For example, when I asked ChatGPT-4 to generate an ASCII image of a mushroom, it provided me with the following output.

It then confidently told me I could use this image of a “mushroom” for my own purposes.

These kinds of overconfident mistakes have been referred to as “ AI hallucinations ” and “ AI bullshit ”. While it is easy to spot that the above ASCII image looks nothing like a mushroom (and quite a bit like a snail), it may be much harder to identify any mistakes ChatGPT makes when surveying scientific literature or describing the state of a philosophical debate.

Unlike (most) humans, AI systems are fundamentally unconcerned with the truth of what they say. If used carelessly, their hallucinations could corrupt the scholarly record.

Should AI-produced text be banned?

One response to the rise of text generators has been to ban them outright. For example, Science – one of the world’s most influential academic journals – disallows any use of AI-generated text .

I see two problems with this approach.

The first problem is a practical one: current tools for detecting AI-generated text are highly unreliable. This includes the detector created by ChatGPT’s own developers, which was taken offline after it was found to have only a 26% accuracy rate (and a 9% false positive rate ). Humans also make mistakes when assessing whether something was written by AI.

It is also possible to circumvent AI text detectors. Online communities are actively exploring how to prompt ChatGPT in ways that allow the user to evade detection. Human users can also superficially rewrite AI outputs, effectively scrubbing away the traces of AI (like its overuse of the words “commendable”, “meticulously” and “intricate”).

The second problem is that banning generative AI outright prevents us from realising these technologies’ benefits. Used well, generative AI can boost academic productivity by streamlining the writing process. In this way, it could help further human knowledge. Ideally, we should try to reap these benefits while avoiding the problems.

The problem is poor quality control, not AI

The most serious problem with AI is the risk of introducing unnoticed errors, leading to sloppy scholarship. Instead of banning AI, we should try to ensure that mistaken, implausible or biased claims cannot make it onto the academic record.

After all, humans can also produce writing with serious errors, and mechanisms such as peer review often fail to prevent its publication.

We need to get better at ensuring academic papers are free from serious mistakes, regardless of whether these mistakes are caused by careless use of AI or sloppy human scholarship. Not only is this more achievable than policing AI usage, it will improve the standards of academic research as a whole.

This would be (as ChatGPT might say) a commendable and meticulously intricate solution.

• Artificial intelligence (AI)
• Academic journals
• Academic publishing
• Hallucinations
• Scholarly publishing
• Academic writing
• Large language models
• Generative AI

Lecturer / Senior Lecturer - Marketing

Research Fellow

Senior Research Fellow - Women's Health Services

Assistant Editor - 1 year cadetship

Executive Dean, Faculty of Health

Paper written using ChatGPT demonstrates opportunities and challenges of AI in academia

ChatGPT has the potential to create increasing and exciting opportunities -- but also poses significant challenges -- for the academic community, according to an innovative study written in large part using the software.

Launched in November 2022, ChatGPT is the latest chatbot and artificial intelligence (AI) platform touted as having the potential to revolutionise research and education.

However, as it becomes ever more advanced, the technology has also prompted concerns across the education sector about academic honesty and plagiarism.

To address some of these, the new study directly uses ChatGPT to demonstrate how sophisticated Large Language Machines (LLMs) have become but also the steps that can be taken to ensure its influence remains a positive one.

Published in the peer-reviewed journal Innovations in Education and Teaching International , the research was conceived by academics from Plymouth Marjon University and the University of Plymouth.

For the majority of the paper, they used a series of prompts and questions to encourage ChatGPT to produce content in an academic style. These included:

• Write an original academic paper, with references, describing the implications of GPT-3 for assessment in higher education;
• How can academics prevent students plagiarising using GPT-3?
• Are there any technologies which will check if work has been written by a chatbot?
• Produce several witty and intelligent titles for an academic research paper on the challenges universities face in ChatGPT and plagiarism.

Once the text was generated, they copied and pasted the output into the manuscript, ordered it broadly following the structure suggested by ChatGPT, and then inserted genuine references throughout.

This process was only revealed to readers in the paper's Discussion section, which was written directly by the researchers without the software's input.

In that section, the study's authors highlight that the text produced by ChatGPT -- while much more sophisticated than previous innovations in this area -- can be relatively formulaic, and that a number of existing AI-detection tools would pick up on that.

However, they say their findings should serve as a wake-up call to university staff to think very carefully about the design of their assessments and ways to ensure that academic dishonesty is clearly explained to students and minimised.

Professor Debby Cotton, Director of Academic Practice and Professor of Higher Education at Plymouth Marjon University, is the study's lead author. She said: "This latest AI development obviously brings huge challenges for universities, not least in testing student knowledge and teaching writing skills -- but looking positively it is an opportunity for us to rethink what we want students to learn and why. I'd like to think that AI would enable us to automate some of the more administrative tasks academics do, allowing more time to be spent working with students"

Corresponding author Dr Peter Cotton, Associate Professor in Ecology at the University of Plymouth, added: "Banning ChatGPT, as was done within New York schools, can only be a short-term solution while we think how to address the issues. AI is already widely accessible to students outside their institutions, and companies like Microsoft and Google are rapidly incorporating it into search engines and Office suites. The chat (sic) is already out of the bag, and the challenge for universities will be to adapt to a paradigm where the use of AI is the expected norm."

Dr Reuben Shipway, Lecturer in Marine Biology at the University of Plymouth, said: "With any new revolutionary technology -- and this is a revolutionary technology -- there will be winners and losers. The losers will be those that fail to adapt to a rapidly changing landscape. The winners will take a pragmatic approach and leverage this technology to their advantage."

• Engineering
• Nanotechnology
• Educational Technology
• Artificial Intelligence
• Education and Employment
• STEM Education
• Educational Policy
• Social science
• Information and communication technologies
• Application software
• Computer software
• Information architecture

Story Source:

Materials provided by University of Plymouth . Original written by Alan Williams. Note: Content may be edited for style and length.

Journal Reference :

• Debby R. E. Cotton, Peter A. Cotton, J. Reuben Shipway. Chatting and cheating: Ensuring academic integrity in the era of ChatGPT . Innovations in Education and Teaching International , 2023; 1 DOI: 10.1080/14703297.2023.2190148

Cite This Page :

Explore More

• Charge Your Laptop in a Minute?
• Caterpillars Detect Predators by Electricity
• 'Electronic Spider Silk' Printed On Human Skin
• Engineered Surfaces Made to Shed Heat
• Innovative Material for Sustainable Building
• Human Brain: New Gene Transcripts
• Epstein-Barr Virus and Resulting Diseases
• Origins of the Proton's Spin
• Symbiotic Bacteria Communicate With Plants
• Birdsong and Human Voice: Same Genetic Blueprint

Trending Topics

Strange & offbeat.

The impact of AI and ChatGPT on research reporting

Affiliations.

• 1 Center for Perioperative Optimization, Department of Surgery, Herlev and Gentofte Hospital, University of Copenhagen, Copenhagen, Denmark.
• 2 Center for Perioperative Optimization, Department of Surgery, Herlev and Gentofte Hospital, University of Copenhagen, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Denmark.
• PMID: 37167941

ChatGPT and the newest GPT-4 are AI language models developed by OpenAI that have gained attention for their potential applications in biomedical research reporting. The models can assist researchers in various stages of writing scientific articles, including literature search, outlining, writing different sections, formatting, and translation. The use of ChatGPT or GPT-4 in research reporting has the potential to speed up the writing process, but its limitations, such as incorrect answers and biases, should also be considered. There is ongoing debate over the issue of AI authorship in scientific papers, with some publishers allowing it to be listed as a contributor in the acknowledgements section, while others do not allow it to be listed as an author. The use of ChatGPT or GPT-4 in research reporting is a recent development, and further studies and discussions are needed to determine their potential and limitations in this field.

• Artificial Intelligence
• Authorship*
• Biomedical Research*
• New Zealand
• Research Personnel

A systematic literature review of empirical research on ChatGPT in education

• Open access
• Published: 26 May 2024
• Volume 3 , article number  60 , ( 2024 )

Cite this article

You have full access to this open access article

• Yazid Albadarin   ORCID: orcid.org/0009-0005-8068-8902 1 ,
• Mohammed Saqr 1 ,
• Nicolas Pope 1 &
• Markku Tukiainen 1  

Over the last four decades, studies have investigated the incorporation of Artificial Intelligence (AI) into education. A recent prominent AI-powered technology that has impacted the education sector is ChatGPT. This article provides a systematic review of 14 empirical studies incorporating ChatGPT into various educational settings, published in 2022 and before the 10th of April 2023—the date of conducting the search process. It carefully followed the essential steps outlined in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, as well as Okoli’s (Okoli in Commun Assoc Inf Syst, 2015) steps for conducting a rigorous and transparent systematic review. In this review, we aimed to explore how students and teachers have utilized ChatGPT in various educational settings, as well as the primary findings of those studies. By employing Creswell’s (Creswell in Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook], Pearson Education, London, 2015) coding techniques for data extraction and interpretation, we sought to gain insight into their initial attempts at ChatGPT incorporation into education. This approach also enabled us to extract insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of this review show that learners have utilized ChatGPT as a virtual intelligent assistant, where it offered instant feedback, on-demand answers, and explanations of complex topics. Additionally, learners have used it to enhance their writing and language skills by generating ideas, composing essays, summarizing, translating, paraphrasing texts, or checking grammar. Moreover, learners turned to it as an aiding tool to facilitate their directed and personalized learning by assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. However, the results of specific studies (n = 3, 21.4%) show that overuse of ChatGPT may negatively impact innovative capacities and collaborative learning competencies among learners. Educators, on the other hand, have utilized ChatGPT to create lesson plans, generate quizzes, and provide additional resources, which helped them enhance their productivity and efficiency and promote different teaching methodologies. Despite these benefits, the majority of the reviewed studies recommend the importance of conducting structured training, support, and clear guidelines for both learners and educators to mitigate the drawbacks. This includes developing critical evaluation skills to assess the accuracy and relevance of information provided by ChatGPT, as well as strategies for integrating human interaction and collaboration into learning activities that involve AI tools. Furthermore, they also recommend ongoing research and proactive dialogue with policymakers, stakeholders, and educational practitioners to refine and enhance the use of AI in learning environments. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Avoid common mistakes on your manuscript.

1 Introduction

Educational technology, a rapidly evolving field, plays a crucial role in reshaping the landscape of teaching and learning [ 82 ]. One of the most transformative technological innovations of our era that has influenced the field of education is Artificial Intelligence (AI) [ 50 ]. Over the last four decades, AI in education (AIEd) has gained remarkable attention for its potential to make significant advancements in learning, instructional methods, and administrative tasks within educational settings [ 11 ]. In particular, a large language model (LLM), a type of AI algorithm that applies artificial neural networks (ANNs) and uses massively large data sets to understand, summarize, generate, and predict new content that is almost difficult to differentiate from human creations [ 79 ], has opened up novel possibilities for enhancing various aspects of education, from content creation to personalized instruction [ 35 ]. Chatbots that leverage the capabilities of LLMs to understand and generate human-like responses have also presented the capacity to enhance student learning and educational outcomes by engaging students, offering timely support, and fostering interactive learning experiences [ 46 ].

The ongoing and remarkable technological advancements in chatbots have made their use more convenient, increasingly natural and effortless, and have expanded their potential for deployment across various domains [ 70 ]. One prominent example of chatbot applications is the Chat Generative Pre-Trained Transformer, known as ChatGPT, which was introduced by OpenAI, a leading AI research lab, on November 30th, 2022. ChatGPT employs a variety of deep learning techniques to generate human-like text, with a particular focus on recurrent neural networks (RNNs). Long short-term memory (LSTM) allows it to grasp the context of the text being processed and retain information from previous inputs. Also, the transformer architecture, a neural network architecture based on the self-attention mechanism, allows it to analyze specific parts of the input, thereby enabling it to produce more natural-sounding and coherent output. Additionally, the unsupervised generative pre-training and the fine-tuning methods allow ChatGPT to generate more relevant and accurate text for specific tasks [ 31 , 62 ]. Furthermore, reinforcement learning from human feedback (RLHF), a machine learning approach that combines reinforcement learning techniques with human-provided feedback, has helped improve ChatGPT’s model by accelerating the learning process and making it significantly more efficient.

This cutting-edge natural language processing (NLP) tool is widely recognized as one of today's most advanced LLMs-based chatbots [ 70 ], allowing users to ask questions and receive detailed, coherent, systematic, personalized, convincing, and informative human-like responses [ 55 ], even within complex and ambiguous contexts [ 63 , 77 ]. ChatGPT is considered the fastest-growing technology in history: in just three months following its public launch, it amassed an estimated 120 million monthly active users [ 16 ] with an estimated 13 million daily queries [ 49 ], surpassing all other applications [ 64 ]. This remarkable growth can be attributed to the unique features and user-friendly interface that ChatGPT offers. Its intuitive design allows users to interact seamlessly with the technology, making it accessible to a diverse range of individuals, regardless of their technical expertise [ 78 ]. Additionally, its exceptional performance results from a combination of advanced algorithms, continuous enhancements, and extensive training on a diverse dataset that includes various text sources such as books, articles, websites, and online forums [ 63 ], have contributed to a more engaging and satisfying user experience [ 62 ]. These factors collectively explain its remarkable global growth and set it apart from predecessors like Bard, Bing Chat, ERNIE, and others.

In this context, several studies have explored the technological advancements of chatbots. One noteworthy recent research effort, conducted by Schöbel et al. [ 70 ], stands out for its comprehensive analysis of more than 5,000 studies on communication agents. This study offered a comprehensive overview of the historical progression and future prospects of communication agents, including ChatGPT. Moreover, other studies have focused on making comparisons, particularly between ChatGPT and alternative chatbots like Bard, Bing Chat, ERNIE, LaMDA, BlenderBot, and various others. For example, O’Leary [ 53 ] compared two chatbots, LaMDA and BlenderBot, with ChatGPT and revealed that ChatGPT outperformed both. This superiority arises from ChatGPT’s capacity to handle a wider range of questions and generate slightly varied perspectives within specific contexts. Similarly, ChatGPT exhibited an impressive ability to formulate interpretable responses that were easily understood when compared with Google's feature snippet [ 34 ]. Additionally, ChatGPT was compared to other LLMs-based chatbots, including Bard and BERT, as well as ERNIE. The findings indicated that ChatGPT exhibited strong performance in the given tasks, often outperforming the other models [ 59 ].

Furthermore, in the education context, a comprehensive study systematically compared a range of the most promising chatbots, including Bard, Bing Chat, ChatGPT, and Ernie across a multidisciplinary test that required higher-order thinking. The study revealed that ChatGPT achieved the highest score, surpassing Bing Chat and Bard [ 64 ]. Similarly, a comparative analysis was conducted to compare ChatGPT with Bard in answering a set of 30 mathematical questions and logic problems, grouped into two question sets. Set (A) is unavailable online, while Set (B) is available online. The results revealed ChatGPT's superiority in Set (A) over Bard. Nevertheless, Bard's advantage emerged in Set (B) due to its capacity to access the internet directly and retrieve answers, a capability that ChatGPT does not possess [ 57 ]. However, through these varied assessments, ChatGPT consistently highlights its exceptional prowess compared to various alternatives in the ever-evolving chatbot technology.

The widespread adoption of chatbots, especially ChatGPT, by millions of students and educators, has sparked extensive discussions regarding its incorporation into the education sector [ 64 ]. Accordingly, many scholars have contributed to the discourse, expressing both optimism and pessimism regarding the incorporation of ChatGPT into education. For example, ChatGPT has been highlighted for its capabilities in enriching the learning and teaching experience through its ability to support different learning approaches, including adaptive learning, personalized learning, and self-directed learning [ 58 , 60 , 91 ]), deliver summative and formative feedback to students and provide real-time responses to questions, increase the accessibility of information [ 22 , 40 , 43 ], foster students’ performance, engagement and motivation [ 14 , 44 , 58 ], and enhance teaching practices [ 17 , 18 , 64 , 74 ].

On the other hand, concerns have been also raised regarding its potential negative effects on learning and teaching. These include the dissemination of false information and references [ 12 , 23 , 61 , 85 ], biased reinforcement [ 47 , 50 ], compromised academic integrity [ 18 , 40 , 66 , 74 ], and the potential decline in students' skills [ 43 , 61 , 64 , 74 ]. As a result, ChatGPT has been banned in multiple countries, including Russia, China, Venezuela, Belarus, and Iran, as well as in various educational institutions in India, Italy, Western Australia, France, and the United States [ 52 , 90 ].

Clearly, the advent of chatbots, especially ChatGPT, has provoked significant controversy due to their potential impact on learning and teaching. This indicates the necessity for further exploration to gain a deeper understanding of this technology and carefully evaluate its potential benefits, limitations, challenges, and threats to education [ 79 ]. Therefore, conducting a systematic literature review will provide valuable insights into the potential prospects and obstacles linked to its incorporation into education. This systematic literature review will primarily focus on ChatGPT, driven by the aforementioned key factors outlined above.

However, the existing literature lacks a systematic literature review of empirical studies. Thus, this systematic literature review aims to address this gap by synthesizing the existing empirical studies conducted on chatbots, particularly ChatGPT, in the field of education, highlighting how ChatGPT has been utilized in educational settings, and identifying any existing gaps. This review may be particularly useful for researchers in the field and educators who are contemplating the integration of ChatGPT or any chatbot into education. The following research questions will guide this study:

What are students' and teachers' initial attempts at utilizing ChatGPT in education?

What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?

2 Methodology

To conduct this study, the authors followed the essential steps of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Okoli’s [ 54 ] steps for conducting a systematic review. These included identifying the study’s purpose, drafting a protocol, applying a practical screening process, searching the literature, extracting relevant data, evaluating the quality of the included studies, synthesizing the studies, and ultimately writing the review. The subsequent section provides an extensive explanation of how these steps were carried out in this study.

2.1 Identify the purpose

Given the widespread adoption of ChatGPT by students and teachers for various educational purposes, often without a thorough understanding of responsible and effective use or a clear recognition of its potential impact on learning and teaching, the authors recognized the need for further exploration of ChatGPT's impact on education in this early stage. Therefore, they have chosen to conduct a systematic literature review of existing empirical studies that incorporate ChatGPT into educational settings. Despite the limited number of empirical studies due to the novelty of the topic, their goal is to gain a deeper understanding of this technology and proactively evaluate its potential benefits, limitations, challenges, and threats to education. This effort could help to understand initial reactions and attempts at incorporating ChatGPT into education and bring out insights and considerations that can inform the future development of education.

2.2 Draft the protocol

The next step is formulating the protocol. This protocol serves to outline the study process in a rigorous and transparent manner, mitigating researcher bias in study selection and data extraction [ 88 ]. The protocol will include the following steps: generating the research question, predefining a literature search strategy, identifying search locations, establishing selection criteria, assessing the studies, developing a data extraction strategy, and creating a timeline.

2.3 Apply practical screen

The screening step aims to accurately filter the articles resulting from the searching step and select the empirical studies that have incorporated ChatGPT into educational contexts, which will guide us in answering the research questions and achieving the objectives of this study. To ensure the rigorous execution of this step, our inclusion and exclusion criteria were determined based on the authors' experience and informed by previous successful systematic reviews [ 21 ]. Table 1 summarizes the inclusion and exclusion criteria for study selection.

2.4 Literature search

We conducted a thorough literature search to identify articles that explored, examined, and addressed the use of ChatGPT in Educational contexts. We utilized two research databases: Dimensions.ai, which provides access to a large number of research publications, and lens.org, which offers access to over 300 million articles, patents, and other research outputs from diverse sources. Additionally, we included three databases, Scopus, Web of Knowledge, and ERIC, which contain relevant research on the topic that addresses our research questions. To browse and identify relevant articles, we used the following search formula: ("ChatGPT" AND "Education"), which included the Boolean operator "AND" to get more specific results. The subject area in the Scopus and ERIC databases were narrowed to "ChatGPT" and "Education" keywords, and in the WoS database was limited to the "Education" category. The search was conducted between the 3rd and 10th of April 2023, which resulted in 276 articles from all selected databases (111 articles from Dimensions.ai, 65 from Scopus, 28 from Web of Science, 14 from ERIC, and 58 from Lens.org). These articles were imported into the Rayyan web-based system for analysis. The duplicates were identified automatically by the system. Subsequently, the first author manually reviewed the duplicated articles ensured that they had the same content, and then removed them, leaving us with 135 unique articles. Afterward, the titles, abstracts, and keywords of the first 40 manuscripts were scanned and reviewed by the first author and were discussed with the second and third authors to resolve any disagreements. Subsequently, the first author proceeded with the filtering process for all articles and carefully applied the inclusion and exclusion criteria as presented in Table  1 . Articles that met any one of the exclusion criteria were eliminated, resulting in 26 articles. Afterward, the authors met to carefully scan and discuss them. The authors agreed to eliminate any empirical studies solely focused on checking ChatGPT capabilities, as these studies do not guide us in addressing the research questions and achieving the study's objectives. This resulted in 14 articles eligible for analysis.

2.5 Quality appraisal

The examination and evaluation of the quality of the extracted articles is a vital step [ 9 ]. Therefore, the extracted articles were carefully evaluated for quality using Fink’s [ 24 ] standards, which emphasize the necessity for detailed descriptions of methodology, results, conclusions, strengths, and limitations. The process began with a thorough assessment of each study's design, data collection, and analysis methods to ensure their appropriateness and comprehensive execution. The clarity, consistency, and logical progression from data to results and conclusions were also critically examined. Potential biases and recognized limitations within the studies were also scrutinized. Ultimately, two articles were excluded for failing to meet Fink’s criteria, particularly in providing sufficient detail on methodology, results, conclusions, strengths, or limitations. The review process is illustrated in Fig.  1 .

The study selection process

2.6 Data extraction

The next step is data extraction, the process of capturing the key information and categories from the included studies. To improve efficiency, reduce variation among authors, and minimize errors in data analysis, the coding categories were constructed using Creswell's [ 15 ] coding techniques for data extraction and interpretation. The coding process involves three sequential steps. The initial stage encompasses open coding , where the researcher examines the data, generates codes to describe and categorize it, and gains a deeper understanding without preconceived ideas. Following open coding is axial coding , where the interrelationships between codes from open coding are analyzed to establish more comprehensive categories or themes. The process concludes with selective coding , refining and integrating categories or themes to identify core concepts emerging from the data. The first coder performed the coding process, then engaged in discussions with the second and third authors to finalize the coding categories for the first five articles. The first coder then proceeded to code all studies and engaged again in discussions with the other authors to ensure the finalization of the coding process. After a comprehensive analysis and capturing of the key information from the included studies, the data extraction and interpretation process yielded several themes. These themes have been categorized and are presented in Table  2 . It is important to note that open coding results were removed from Table  2 for aesthetic reasons, as it included many generic aspects, such as words, short phrases, or sentences mentioned in the studies.

2.7 Synthesize studies

In this stage, we will gather, discuss, and analyze the key findings that emerged from the selected studies. The synthesis stage is considered a transition from an author-centric to a concept-centric focus, enabling us to map all the provided information to achieve the most effective evaluation of the data [ 87 ]. Initially, the authors extracted data that included general information about the selected studies, including the author(s)' names, study titles, years of publication, educational levels, research methodologies, sample sizes, participants, main aims or objectives, raw data sources, and analysis methods. Following that, all key information and significant results from the selected studies were compiled using Creswell’s [ 15 ] coding techniques for data extraction and interpretation to identify core concepts and themes emerging from the data, focusing on those that directly contributed to our research questions and objectives, such as the initial utilization of ChatGPT in learning and teaching, learners' and educators' familiarity with ChatGPT, and the main findings of each study. Finally, the data related to each selected study were extracted into an Excel spreadsheet for data processing. The Excel spreadsheet was reviewed by the authors, including a series of discussions to ensure the finalization of this process and prepare it for further analysis. Afterward, the final result being analyzed and presented in various types of charts and graphs. Table 4 presents the extracted data from the selected studies, with each study labeled with a capital 'S' followed by a number.

This section consists of two main parts. The first part provides a descriptive analysis of the data compiled from the reviewed studies. The second part presents the answers to the research questions and the main findings of these studies.

3.1 Part 1: descriptive analysis

This section will provide a descriptive analysis of the reviewed studies, including educational levels and fields, participants distribution, country contribution, research methodologies, study sample size, study population, publication year, list of journals, familiarity with ChatGPT, source of data, and the main aims and objectives of the studies. Table 4 presents a comprehensive overview of the extracted data from the selected studies.

3.1.1 The number of the reviewed studies and publication years

The total number of the reviewed studies was 14. All studies were empirical studies and published in different journals focusing on Education and Technology. One study was published in 2022 [S1], while the remaining were published in 2023 [S2]-[S14]. Table 3 illustrates the year of publication, the names of the journals, and the number of reviewed studies published in each journal for the studies reviewed.

3.1.2 Educational levels and fields

The majority of the reviewed studies, 11 studies, were conducted in higher education institutions [S1]-[S10] and [S13]. Two studies did not specify the educational level of the population [S12] and [S14], while one study focused on elementary education [S11]. However, the reviewed studies covered various fields of education. Three studies focused on Arts and Humanities Education [S8], [S11], and [S14], specifically English Education. Two studies focused on Engineering Education, with one in Computer Engineering [S2] and the other in Construction Education [S3]. Two studies focused on Mathematics Education [S5] and [S12]. One study focused on Social Science Education [S13]. One study focused on Early Education [S4]. One study focused on Journalism Education [S9]. Finally, three studies did not specify the field of education [S1], [S6], and [S7]. Figure  2 represents the educational levels in the reviewed studies, while Fig.  3 represents the context of the reviewed studies.

Educational levels in the reviewed studies

Context of the reviewed studies

3.1.3 Participants distribution and countries contribution

The reviewed studies have been conducted across different geographic regions, providing a diverse representation of the studies. The majority of the studies, 10 in total, [S1]-[S3], [S5]-[S9], [S11], and [S14], primarily focused on participants from single countries such as Pakistan, the United Arab Emirates, China, Indonesia, Poland, Saudi Arabia, South Korea, Spain, Tajikistan, and the United States. In contrast, four studies, [S4], [S10], [S12], and [S13], involved participants from multiple countries, including China and the United States [S4], China, the United Kingdom, and the United States [S10], the United Arab Emirates, Oman, Saudi Arabia, and Jordan [S12], Turkey, Sweden, Canada, and Australia [ 13 ]. Figures  4 and 5 illustrate the distribution of participants, whether from single or multiple countries, and the contribution of each country in the reviewed studies, respectively.

The reviewed studies conducted in single or multiple countries

The Contribution of each country in the studies

3.1.4 Study population and sample size

Four study populations were included: university students, university teachers, university teachers and students, and elementary school teachers. Six studies involved university students [S2], [S3], [S5] and [S6]-[S8]. Three studies focused on university teachers [S1], [S4], and [S6], while one study specifically targeted elementary school teachers [S11]. Additionally, four studies included both university teachers and students [S10] and [ 12 , 13 , 14 ], and among them, study [S13] specifically included postgraduate students. In terms of the sample size of the reviewed studies, nine studies included a small sample size of less than 50 participants [S1], [S3], [S6], [S8], and [S10]-[S13]. Three studies had 50–100 participants [S2], [S9], and [S14]. Only one study had more than 100 participants [S7]. It is worth mentioning that study [S4] adopted a mixed methods approach, including 10 participants for qualitative analysis and 110 participants for quantitative analysis.

3.1.5 Participants’ familiarity with using ChatGPT

The reviewed studies recruited a diverse range of participants with varying levels of familiarity with ChatGPT. Five studies [S2], [S4], [S6], [S8], and [S12] involved participants already familiar with ChatGPT, while eight studies [S1], [S3], [S5], [S7], [S9], [S10], [S13] and [S14] included individuals with differing levels of familiarity. Notably, one study [S11] had participants who were entirely unfamiliar with ChatGPT. It is important to note that four studies [S3], [S5], [S9], and [S11] provided training or guidance to their participants before conducting their studies, while ten studies [S1], [S2], [S4], [S6]-[S8], [S10], and [S12]-[S14] did not provide training due to the participants' existing familiarity with ChatGPT.

3.1.6 Research methodology approaches and source(S) of data

The reviewed studies adopted various research methodology approaches. Seven studies adopted qualitative research methodology [S1], [S4], [S6], [S8], [S10], [S11], and [S12], while three studies adopted quantitative research methodology [S3], [S7], and [S14], and four studies employed mixed-methods, which involved a combination of both the strengths of qualitative and quantitative methods [S2], [S5], [S9], and [S13].

In terms of the source(s) of data, the reviewed studies obtained their data from various sources, such as interviews, questionnaires, and pre-and post-tests. Six studies relied on interviews as their primary source of data collection [S1], [S4], [S6], [S10], [S11], and [S12], four studies relied on questionnaires [S2], [S7], [S13], and [S14], two studies combined the use of pre-and post-tests and questionnaires for data collection [S3] and [S9], while two studies combined the use of questionnaires and interviews to obtain the data [S5] and [S8]. It is important to note that six of the reviewed studies were quasi-experimental [S3], [S5], [S8], [S9], [S12], and [S14], while the remaining ones were experimental studies [S1], [S2], [S4], [S6], [S7], [S10], [S11], and [S13]. Figures  6 and 7 illustrate the research methodologies and the source (s) of data used in the reviewed studies, respectively.

Research methodologies in the reviewed studies

Source of data in the reviewed studies

3.1.7 The aim and objectives of the studies

The reviewed studies encompassed a diverse set of aims, with several of them incorporating multiple primary objectives. Six studies [S3], [S6], [S7], [S8], [S11], and [S12] examined the integration of ChatGPT in educational contexts, and four studies [S4], [S5], [S13], and [S14] investigated the various implications of its use in education, while three studies [S2], [S9], and [S10] aimed to explore both its integration and implications in education. Additionally, seven studies explicitly explored attitudes and perceptions of students [S2] and [S3], educators [S1] and [S6], or both [S10], [S12], and [S13] regarding the utilization of ChatGPT in educational settings.

3.2 Part 2: research questions and main findings of the reviewed studies

This part will present the answers to the research questions and the main findings of the reviewed studies, classified into two main categories (learning and teaching) according to AI Education classification by [ 36 ]. Figure  8 summarizes the main findings of the reviewed studies in a visually informative diagram. Table 4 provides a detailed list of the key information extracted from the selected studies that led to generating these themes.

The main findings in the reviewed studies

4 Students' initial attempts at utilizing ChatGPT in learning and main findings from students' perspective

4.1 virtual intelligent assistant.

Nine studies demonstrated that ChatGPT has been utilized by students as an intelligent assistant to enhance and support their learning. Students employed it for various purposes, such as answering on-demand questions [S2]-[S5], [S8], [S10], and [S12], providing valuable information and learning resources [S2]-[S5], [S6], and [S8], as well as receiving immediate feedback [S2], [S4], [S9], [S10], and [S12]. In this regard, students generally were confident in the accuracy of ChatGPT's responses, considering them relevant, reliable, and detailed [S3], [S4], [S5], and [S8]. However, some students indicated the need for improvement, as they found that answers are not always accurate [S2], and that misleading information may have been provided or that it may not always align with their expectations [S6] and [S10]. It was also observed by the students that the accuracy of ChatGPT is dependent on several factors, including the quality and specificity of the user's input, the complexity of the question or topic, and the scope and relevance of its training data [S12]. Many students felt that ChatGPT's answers were not always accurate and most of them believed that it requires good background knowledge to work with.

4.2 Writing and language proficiency assistant

Six of the reviewed studies highlighted that ChatGPT has been utilized by students as a valuable assistant tool to improve their academic writing skills and language proficiency. Among these studies, three mainly focused on English education, demonstrating that students showed sufficient mastery in using ChatGPT for generating ideas, summarizing, paraphrasing texts, and completing writing essays [S8], [S11], and [S14]. Furthermore, ChatGPT helped them in writing by making students active investigators rather than passive knowledge recipients and facilitated the development of their writing skills [S11] and [S14]. Similarly, ChatGPT allowed students to generate unique ideas and perspectives, leading to deeper analysis and reflection on their journalism writing [S9]. In terms of language proficiency, ChatGPT allowed participants to translate content into their home languages, making it more accessible and relevant to their context [S4]. It also enabled them to request changes in linguistic tones or flavors [S8]. Moreover, participants used it to check grammar or as a dictionary [S11].

4.3 Valuable resource for learning approaches

Five studies demonstrated that students used ChatGPT as a valuable complementary resource for self-directed learning. It provided learning resources and guidance on diverse educational topics and created a supportive home learning environment [S2] and [S4]. Moreover, it offered step-by-step guidance to grasp concepts at their own pace and enhance their understanding [S5], streamlined task and project completion carried out independently [S7], provided comprehensive and easy-to-understand explanations on various subjects [S10], and assisted in studying geometry operations, thereby empowering them to explore geometry operations at their own pace [S12]. Three studies showed that students used ChatGPT as a valuable learning resource for personalized learning. It delivered age-appropriate conversations and tailored teaching based on a child's interests [S4], acted as a personalized learning assistant, adapted to their needs and pace, which assisted them in understanding mathematical concepts [S12], and enabled personalized learning experiences in social sciences by adapting to students' needs and learning styles [S13]. On the other hand, it is important to note that, according to one study [S5], students suggested that using ChatGPT may negatively affect collaborative learning competencies between students.

4.4 Enhancing students' competencies

Six of the reviewed studies have shown that ChatGPT is a valuable tool for improving a wide range of skills among students. Two studies have provided evidence that ChatGPT led to improvements in students' critical thinking, reasoning skills, and hazard recognition competencies through engaging them in interactive conversations or activities and providing responses related to their disciplines in journalism [S5] and construction education [S9]. Furthermore, two studies focused on mathematical education have shown the positive impact of ChatGPT on students' problem-solving abilities in unraveling problem-solving questions [S12] and enhancing the students' understanding of the problem-solving process [S5]. Lastly, one study indicated that ChatGPT effectively contributed to the enhancement of conversational social skills [S4].

4.5 Supporting students' academic success

Seven of the reviewed studies highlighted that students found ChatGPT to be beneficial for learning as it enhanced learning efficiency and improved the learning experience. It has been observed to improve students' efficiency in computer engineering studies by providing well-structured responses and good explanations [S2]. Additionally, students found it extremely useful for hazard reporting [S3], and it also enhanced their efficiency in solving mathematics problems and capabilities [S5] and [S12]. Furthermore, by finding information, generating ideas, translating texts, and providing alternative questions, ChatGPT aided students in deepening their understanding of various subjects [S6]. It contributed to an increase in students' overall productivity [S7] and improved efficiency in composing written tasks [S8]. Regarding learning experiences, ChatGPT was instrumental in assisting students in identifying hazards that they might have otherwise overlooked [S3]. It also improved students' learning experiences in solving mathematics problems and developing abilities [S5] and [S12]. Moreover, it increased students' successful completion of important tasks in their studies [S7], particularly those involving average difficulty writing tasks [S8]. Additionally, ChatGPT increased the chances of educational success by providing students with baseline knowledge on various topics [S10].

5 Teachers' initial attempts at utilizing ChatGPT in teaching and main findings from teachers' perspective

5.1 valuable resource for teaching.

The reviewed studies showed that teachers have employed ChatGPT to recommend, modify, and generate diverse, creative, organized, and engaging educational contents, teaching materials, and testing resources more rapidly [S4], [S6], [S10] and [S11]. Additionally, teachers experienced increased productivity as ChatGPT facilitated quick and accurate responses to questions, fact-checking, and information searches [S1]. It also proved valuable in constructing new knowledge [S6] and providing timely answers to students' questions in classrooms [S11]. Moreover, ChatGPT enhanced teachers' efficiency by generating new ideas for activities and preplanning activities for their students [S4] and [S6], including interactive language game partners [S11].

5.2 Improving productivity and efficiency

The reviewed studies showed that participants' productivity and work efficiency have been significantly enhanced by using ChatGPT as it enabled them to allocate more time to other tasks and reduce their overall workloads [S6], [S10], [S11], [S13], and [S14]. However, three studies [S1], [S4], and [S11], indicated a negative perception and attitude among teachers toward using ChatGPT. This negativity stemmed from a lack of necessary skills to use it effectively [S1], a limited familiarity with it [S4], and occasional inaccuracies in the content provided by it [S10].

5.3 Catalyzing new teaching methodologies

Five of the reviewed studies highlighted that educators found the necessity of redefining their teaching profession with the assistance of ChatGPT [S11], developing new effective learning strategies [S4], and adapting teaching strategies and methodologies to ensure the development of essential skills for future engineers [S5]. They also emphasized the importance of adopting new educational philosophies and approaches that can evolve with the introduction of ChatGPT into the classroom [S12]. Furthermore, updating curricula to focus on improving human-specific features, such as emotional intelligence, creativity, and philosophical perspectives [S13], was found to be essential.

5.4 Effective utilization of CHATGPT in teaching

According to the reviewed studies, effective utilization of ChatGPT in education requires providing teachers with well-structured training, support, and adequate background on how to use ChatGPT responsibly [S1], [S3], [S11], and [S12]. Establishing clear rules and regulations regarding its usage is essential to ensure it positively impacts the teaching and learning processes, including students' skills [S1], [S4], [S5], [S8], [S9], and [S11]-[S14]. Moreover, conducting further research and engaging in discussions with policymakers and stakeholders is indeed crucial for the successful integration of ChatGPT in education and to maximize the benefits for both educators and students [S1], [S6]-[S10], and [S12]-[S14].

6 Discussion

The purpose of this review is to conduct a systematic review of empirical studies that have explored the utilization of ChatGPT, one of today’s most advanced LLM-based chatbots, in education. The findings of the reviewed studies showed several ways of ChatGPT utilization in different learning and teaching practices as well as it provided insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of the reviewed studies came from diverse fields of education, which helped us avoid a biased review that is limited to a specific field. Similarly, the reviewed studies have been conducted across different geographic regions. This kind of variety in geographic representation enriched the findings of this review.

In response to RQ1 , "What are students' and teachers' initial attempts at utilizing ChatGPT in education?", the findings from this review provide comprehensive insights. Chatbots, including ChatGPT, play a crucial role in supporting student learning, enhancing their learning experiences, and facilitating diverse learning approaches [ 42 , 43 ]. This review found that this tool, ChatGPT, has been instrumental in enhancing students' learning experiences by serving as a virtual intelligent assistant, providing immediate feedback, on-demand answers, and engaging in educational conversations. Additionally, students have benefited from ChatGPT’s ability to generate ideas, compose essays, and perform tasks like summarizing, translating, paraphrasing texts, or checking grammar, thereby enhancing their writing and language competencies. Furthermore, students have turned to ChatGPT for assistance in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks, which fosters a supportive home learning environment, allowing them to take responsibility for their own learning and cultivate the skills and approaches essential for supportive home learning environment [ 26 , 27 , 28 ]. This finding aligns with the study of Saqr et al. [ 68 , 69 ] who highlighted that, when students actively engage in their own learning process, it yields additional advantages, such as heightened motivation, enhanced achievement, and the cultivation of enthusiasm, turning them into advocates for their own learning.

Moreover, students have utilized ChatGPT for tailored teaching and step-by-step guidance on diverse educational topics, streamlining task and project completion, and generating and recommending educational content. This personalization enhances the learning environment, leading to increased academic success. This finding aligns with other recent studies [ 26 , 27 , 28 , 60 , 66 ] which revealed that ChatGPT has the potential to offer personalized learning experiences and support an effective learning process by providing students with customized feedback and explanations tailored to their needs and abilities. Ultimately, fostering students' performance, engagement, and motivation, leading to increase students' academic success [ 14 , 44 , 58 ]. This ultimate outcome is in line with the findings of Saqr et al. [ 68 , 69 ], which emphasized that learning strategies are important catalysts of students' learning, as students who utilize effective learning strategies are more likely to have better academic achievement.

Teachers, too, have capitalized on ChatGPT's capabilities to enhance productivity and efficiency, using it for creating lesson plans, generating quizzes, providing additional resources, generating and preplanning new ideas for activities, and aiding in answering students’ questions. This adoption of technology introduces new opportunities to support teaching and learning practices, enhancing teacher productivity. This finding aligns with those of Day [ 17 ], De Castro [ 18 ], and Su and Yang [ 74 ] as well as with those of Valtonen et al. [ 82 ], who revealed that emerging technological advancements have opened up novel opportunities and means to support teaching and learning practices, and enhance teachers’ productivity.

In response to RQ2 , "What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?", the findings from this review provide profound insights and raise significant concerns. Starting with the insights, chatbots, including ChatGPT, have demonstrated the potential to reshape and revolutionize education, creating new, novel opportunities for enhancing the learning process and outcomes [ 83 ], facilitating different learning approaches, and offering a range of pedagogical benefits [ 19 , 43 , 72 ]. In this context, this review found that ChatGPT could open avenues for educators to adopt or develop new effective learning and teaching strategies that can evolve with the introduction of ChatGPT into the classroom. Nonetheless, there is an evident lack of research understanding regarding the potential impact of generative machine learning models within diverse educational settings [ 83 ]. This necessitates teachers to attain a high level of proficiency in incorporating chatbots, such as ChatGPT, into their classrooms to create inventive, well-structured, and captivating learning strategies. In the same vein, the review also found that teachers without the requisite skills to utilize ChatGPT realized that it did not contribute positively to their work and could potentially have adverse effects [ 37 ]. This concern could lead to inequity of access to the benefits of chatbots, including ChatGPT, as individuals who lack the necessary expertise may not be able to harness their full potential, resulting in disparities in educational outcomes and opportunities. Therefore, immediate action is needed to address these potential issues. A potential solution is offering training, support, and competency development for teachers to ensure that all of them can leverage chatbots, including ChatGPT, effectively and equitably in their educational practices [ 5 , 28 , 80 ], which could enhance accessibility and inclusivity, and potentially result in innovative outcomes [ 82 , 83 ].

Additionally, chatbots, including ChatGPT, have the potential to significantly impact students' thinking abilities, including retention, reasoning, analysis skills [ 19 , 45 ], and foster innovation and creativity capabilities [ 83 ]. This review found that ChatGPT could contribute to improving a wide range of skills among students. However, it found that frequent use of ChatGPT may result in a decrease in innovative capacities, collaborative skills and cognitive capacities, and students' motivation to attend classes, as well as could lead to reduced higher-order thinking skills among students [ 22 , 29 ]. Therefore, immediate action is needed to carefully examine the long-term impact of chatbots such as ChatGPT, on learning outcomes as well as to explore its incorporation into educational settings as a supportive tool without compromising students' cognitive development and critical thinking abilities. In the same vein, the review also found that it is challenging to draw a consistent conclusion regarding the potential of ChatGPT to aid self-directed learning approach. This finding aligns with the recent study of Baskara [ 8 ]. Therefore, further research is needed to explore the potential of ChatGPT for self-directed learning. One potential solution involves utilizing learning analytics as a novel approach to examine various aspects of students' learning and support them in their individual endeavors [ 32 ]. This approach can bridge this gap by facilitating an in-depth analysis of how learners engage with ChatGPT, identifying trends in self-directed learning behavior, and assessing its influence on their outcomes.

Turning to the significant concerns, on the other hand, a fundamental challenge with LLM-based chatbots, including ChatGPT, is the accuracy and quality of the provided information and responses, as they provide false information as truth—a phenomenon often referred to as "hallucination" [ 3 , 49 ]. In this context, this review found that the provided information was not entirely satisfactory. Consequently, the utilization of chatbots presents potential concerns, such as generating and providing inaccurate or misleading information, especially for students who utilize it to support their learning. This finding aligns with other findings [ 6 , 30 , 35 , 40 ] which revealed that incorporating chatbots such as ChatGPT, into education presents challenges related to its accuracy and reliability due to its training on a large corpus of data, which may contain inaccuracies and the way users formulate or ask ChatGPT. Therefore, immediate action is needed to address these potential issues. One possible solution is to equip students with the necessary skills and competencies, which include a background understanding of how to use it effectively and the ability to assess and evaluate the information it generates, as the accuracy and the quality of the provided information depend on the input, its complexity, the topic, and the relevance of its training data [ 28 , 49 , 86 ]. However, it's also essential to examine how learners can be educated about how these models operate, the data used in their training, and how to recognize their limitations, challenges, and issues [ 79 ].

Furthermore, chatbots present a substantial challenge concerning maintaining academic integrity [ 20 , 56 ] and copyright violations [ 83 ], which are significant concerns in education. The review found that the potential misuse of ChatGPT might foster cheating, facilitate plagiarism, and threaten academic integrity. This issue is also affirmed by the research conducted by Basic et al. [ 7 ], who presented evidence that students who utilized ChatGPT in their writing assignments had more plagiarism cases than those who did not. These findings align with the conclusions drawn by Cotton et al. [ 13 ], Hisan and Amri [ 33 ] and Sullivan et al. [ 75 ], who revealed that the integration of chatbots such as ChatGPT into education poses a significant challenge to the preservation of academic integrity. Moreover, chatbots, including ChatGPT, have increased the difficulty in identifying plagiarism [ 47 , 67 , 76 ]. The findings from previous studies [ 1 , 84 ] indicate that AI-generated text often went undetected by plagiarism software, such as Turnitin. However, Turnitin and other similar plagiarism detection tools, such as ZeroGPT, GPTZero, and Copyleaks, have since evolved, incorporating enhanced techniques to detect AI-generated text, despite the possibility of false positives, as noted in different studies that have found these tools still not yet fully ready to accurately and reliably identify AI-generated text [ 10 , 51 ], and new novel detection methods may need to be created and implemented for AI-generated text detection [ 4 ]. This potential issue could lead to another concern, which is the difficulty of accurately evaluating student performance when they utilize chatbots such as ChatGPT assistance in their assignments. Consequently, the most LLM-driven chatbots present a substantial challenge to traditional assessments [ 64 ]. The findings from previous studies indicate the importance of rethinking, improving, and redesigning innovative assessment methods in the era of chatbots [ 14 , 20 , 64 , 75 ]. These methods should prioritize the process of evaluating students' ability to apply knowledge to complex cases and demonstrate comprehension, rather than solely focusing on the final product for assessment. Therefore, immediate action is needed to address these potential issues. One possible solution would be the development of clear guidelines, regulatory policies, and pedagogical guidance. These measures would help regulate the proper and ethical utilization of chatbots, such as ChatGPT, and must be established before their introduction to students [ 35 , 38 , 39 , 41 , 89 ].

In summary, our review has delved into the utilization of ChatGPT, a prominent example of chatbots, in education, addressing the question of how ChatGPT has been utilized in education. However, there remain significant gaps, which necessitate further research to shed light on this area.

7 Conclusions

This systematic review has shed light on the varied initial attempts at incorporating ChatGPT into education by both learners and educators, while also offering insights and considerations that can facilitate its effective and responsible use in future educational contexts. From the analysis of 14 selected studies, the review revealed the dual-edged impact of ChatGPT in educational settings. On the positive side, ChatGPT significantly aided the learning process in various ways. Learners have used it as a virtual intelligent assistant, benefiting from its ability to provide immediate feedback, on-demand answers, and easy access to educational resources. Additionally, it was clear that learners have used it to enhance their writing and language skills, engaging in practices such as generating ideas, composing essays, and performing tasks like summarizing, translating, paraphrasing texts, or checking grammar. Importantly, other learners have utilized it in supporting and facilitating their directed and personalized learning on a broad range of educational topics, assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. Educators, on the other hand, found ChatGPT beneficial for enhancing productivity and efficiency. They used it for creating lesson plans, generating quizzes, providing additional resources, and answers learners' questions, which saved time and allowed for more dynamic and engaging teaching strategies and methodologies.

However, the review also pointed out negative impacts. The results revealed that overuse of ChatGPT could decrease innovative capacities and collaborative learning among learners. Specifically, relying too much on ChatGPT for quick answers can inhibit learners' critical thinking and problem-solving skills. Learners might not engage deeply with the material or consider multiple solutions to a problem. This tendency was particularly evident in group projects, where learners preferred consulting ChatGPT individually for solutions over brainstorming and collaborating with peers, which negatively affected their teamwork abilities. On a broader level, integrating ChatGPT into education has also raised several concerns, including the potential for providing inaccurate or misleading information, issues of inequity in access, challenges related to academic integrity, and the possibility of misusing the technology.

Accordingly, this review emphasizes the urgency of developing clear rules, policies, and regulations to ensure ChatGPT's effective and responsible use in educational settings, alongside other chatbots, by both learners and educators. This requires providing well-structured training to educate them on responsible usage and understanding its limitations, along with offering sufficient background information. Moreover, it highlights the importance of rethinking, improving, and redesigning innovative teaching and assessment methods in the era of ChatGPT. Furthermore, conducting further research and engaging in discussions with policymakers and stakeholders are essential steps to maximize the benefits for both educators and learners and ensure academic integrity.

It is important to acknowledge that this review has certain limitations. Firstly, the limited inclusion of reviewed studies can be attributed to several reasons, including the novelty of the technology, as new technologies often face initial skepticism and cautious adoption; the lack of clear guidelines or best practices for leveraging this technology for educational purposes; and institutional or governmental policies affecting the utilization of this technology in educational contexts. These factors, in turn, have affected the number of studies available for review. Secondly, the utilization of the original version of ChatGPT, based on GPT-3 or GPT-3.5, implies that new studies utilizing the updated version, GPT-4 may lead to different findings. Therefore, conducting follow-up systematic reviews is essential once more empirical studies on ChatGPT are published. Additionally, long-term studies are necessary to thoroughly examine and assess the impact of ChatGPT on various educational practices.

Despite these limitations, this systematic review has highlighted the transformative potential of ChatGPT in education, revealing its diverse utilization by learners and educators alike and summarized the benefits of incorporating it into education, as well as the forefront critical concerns and challenges that must be addressed to facilitate its effective and responsible use in future educational contexts. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Data availability

The data supporting our findings are available upon request.

Abbreviations

• Artificial intelligence

AI in education

Large language model

Artificial neural networks

Chat Generative Pre-Trained Transformer

Recurrent neural networks

Long short-term memory

Reinforcement learning from human feedback

Natural language processing

Preferred Reporting Items for Systematic Reviews and Meta-Analyses

AlAfnan MA, Dishari S, Jovic M, Lomidze K. ChatGPT as an educational tool: opportunities, challenges, and recommendations for communication, business writing, and composition courses. J Artif Intell Technol. 2023. https://doi.org/10.37965/jait.2023.0184 .

Article   Google Scholar  

Ali JKM, Shamsan MAA, Hezam TA, Mohammed AAQ. Impact of ChatGPT on learning motivation. J Engl Stud Arabia Felix. 2023;2(1):41–9. https://doi.org/10.56540/jesaf.v2i1.51 .

Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus. 2023. https://doi.org/10.7759/cureus.35179 .

Anderson N, Belavý DL, Perle SM, Hendricks S, Hespanhol L, Verhagen E, Memon AR. AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in sports & exercise medicine manuscript generation. BMJ Open Sport Exerc Med. 2023;9(1): e001568. https://doi.org/10.1136/bmjsem-2023-001568 .

Ausat AMA, Massang B, Efendi M, Nofirman N, Riady Y. Can chat GPT replace the role of the teacher in the classroom: a fundamental analysis. J Educ. 2023;5(4):16100–6.

Google Scholar  

Baidoo-Anu D, Ansah L. Education in the Era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4337484 .

Basic Z, Banovac A, Kruzic I, Jerkovic I. Better by you, better than me, chatgpt3 as writing assistance in students essays. 2023. arXiv preprint arXiv:2302.04536 .‏

Baskara FR. The promises and pitfalls of using chat GPT for self-determined learning in higher education: an argumentative review. Prosiding Seminar Nasional Fakultas Tarbiyah dan Ilmu Keguruan IAIM Sinjai. 2023;2:95–101. https://doi.org/10.47435/sentikjar.v2i0.1825 .

Behera RK, Bala PK, Dhir A. The emerging role of cognitive computing in healthcare: a systematic literature review. Int J Med Inform. 2019;129:154–66. https://doi.org/10.1016/j.ijmedinf.2019.04.024 .

Chaka C. Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: the case of five AI content detection tools. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.2.12 .

Chiu TKF, Xia Q, Zhou X, Chai CS, Cheng M. Systematic literature review on opportunities, challenges, and future research recommendations of artificial intelligence in education. Comput Educ Artif Intell. 2023;4:100118. https://doi.org/10.1016/j.caeai.2022.100118 .

Choi EPH, Lee JJ, Ho M, Kwok JYY, Lok KYW. Chatting or cheating? The impacts of ChatGPT and other artificial intelligence language models on nurse education. Nurse Educ Today. 2023;125:105796. https://doi.org/10.1016/j.nedt.2023.105796 .

Cotton D, Cotton PA, Shipway JR. Chatting and cheating: ensuring academic integrity in the era of ChatGPT. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2190148 .

Crawford J, Cowling M, Allen K. Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.3.02 .

Creswell JW. Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook]. 4th ed. London: Pearson Education; 2015.

Curry D. ChatGPT Revenue and Usage Statistics (2023)—Business of Apps. 2023. https://www.businessofapps.com/data/chatgpt-statistics/

Day T. A preliminary investigation of fake peer-reviewed citations and references generated by ChatGPT. Prof Geogr. 2023. https://doi.org/10.1080/00330124.2023.2190373 .

De Castro CA. A Discussion about the Impact of ChatGPT in education: benefits and concerns. J Bus Theor Pract. 2023;11(2):p28. https://doi.org/10.22158/jbtp.v11n2p28 .

Deng X, Yu Z. A meta-analysis and systematic review of the effect of Chatbot technology use in sustainable education. Sustainability. 2023;15(4):2940. https://doi.org/10.3390/su15042940 .

Eke DO. ChatGPT and the rise of generative AI: threat to academic integrity? J Responsib Technol. 2023;13:100060. https://doi.org/10.1016/j.jrt.2023.100060 .

Elmoazen R, Saqr M, Tedre M, Hirsto L. A systematic literature review of empirical research on epistemic network analysis in education. IEEE Access. 2022;10:17330–48. https://doi.org/10.1109/access.2022.3149812 .

Farrokhnia M, Banihashem SK, Noroozi O, Wals AEJ. A SWOT analysis of ChatGPT: implications for educational practice and research. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2195846 .

Fergus S, Botha M, Ostovar M. Evaluating academic answers generated using ChatGPT. J Chem Educ. 2023;100(4):1672–5. https://doi.org/10.1021/acs.jchemed.3c00087 .

Fink A. Conducting research literature reviews: from the Internet to Paper. Incorporated: SAGE Publications; 2010.

Firaina R, Sulisworo D. Exploring the usage of ChatGPT in higher education: frequency and impact on productivity. Buletin Edukasi Indonesia (BEI). 2023;2(01):39–46. https://doi.org/10.56741/bei.v2i01.310 .

Firat, M. (2023). How chat GPT can transform autodidactic experiences and open education.  Department of Distance Education, Open Education Faculty, Anadolu Unive .‏ https://orcid.org/0000-0001-8707-5918

Firat M. What ChatGPT means for universities: perceptions of scholars and students. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.22 .

Fuchs K. Exploring the opportunities and challenges of NLP models in higher education: is Chat GPT a blessing or a curse? Front Educ. 2023. https://doi.org/10.3389/feduc.2023.1166682 .

García-Peñalvo FJ. La percepción de la inteligencia artificial en contextos educativos tras el lanzamiento de ChatGPT: disrupción o pánico. Educ Knowl Soc. 2023;24: e31279. https://doi.org/10.14201/eks.31279 .

Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor A, Chartash D. How does ChatGPT perform on the United States medical Licensing examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9: e45312. https://doi.org/10.2196/45312 .

Hashana AJ, Brundha P, Ayoobkhan MUA, Fazila S. Deep Learning in ChatGPT—A Survey. In   2023 7th international conference on trends in electronics and informatics (ICOEI) . 2023. (pp. 1001–1005). IEEE. https://doi.org/10.1109/icoei56765.2023.10125852

Hirsto L, Saqr M, López-Pernas S, Valtonen T. (2022). A systematic narrative review of learning analytics research in K-12 and schools.  Proceedings . https://ceur-ws.org/Vol-3383/FLAIEC22_paper_9536.pdf

Hisan UK, Amri MM. ChatGPT and medical education: a double-edged sword. J Pedag Educ Sci. 2023;2(01):71–89. https://doi.org/10.13140/RG.2.2.31280.23043/1 .

Hopkins AM, Logan JM, Kichenadasse G, Sorich MJ. Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 2023. https://doi.org/10.1093/jncics/pkad010 .

Househ M, AlSaad R, Alhuwail D, Ahmed A, Healy MG, Latifi S, Sheikh J. Large Language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9: e48291. https://doi.org/10.2196/48291 .

Ilkka T. The impact of artificial intelligence on learning, teaching, and education. Minist de Educ. 2018. https://doi.org/10.2760/12297 .

Iqbal N, Ahmed H, Azhar KA. Exploring teachers’ attitudes towards using CHATGPT. Globa J Manag Adm Sci. 2022;3(4):97–111. https://doi.org/10.46568/gjmas.v3i4.163 .

Irfan M, Murray L, Ali S. Integration of Artificial intelligence in academia: a case study of critical teaching and learning in Higher education. Globa Soc Sci Rev. 2023;8(1):352–64. https://doi.org/10.31703/gssr.2023(viii-i).32 .

Jeon JH, Lee S. Large language models in education: a focus on the complementary relationship between human teachers and ChatGPT. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11834-1 .

Khan RA, Jawaid M, Khan AR, Sajjad M. ChatGPT—Reshaping medical education and clinical management. Pak J Med Sci. 2023. https://doi.org/10.12669/pjms.39.2.7653 .

King MR. A conversation on artificial intelligence, Chatbots, and plagiarism in higher education. Cell Mol Bioeng. 2023;16(1):1–2. https://doi.org/10.1007/s12195-022-00754-8 .

Kooli C. Chatbots in education and research: a critical examination of ethical implications and solutions. Sustainability. 2023;15(7):5614. https://doi.org/10.3390/su15075614 .

Kuhail MA, Alturki N, Alramlawi S, Alhejori K. Interacting with educational chatbots: a systematic review. Educ Inf Technol. 2022;28(1):973–1018. https://doi.org/10.1007/s10639-022-11177-3 .

Lee H. The rise of ChatGPT: exploring its potential in medical education. Anat Sci Educ. 2023. https://doi.org/10.1002/ase.2270 .

Li L, Subbareddy R, Raghavendra CG. AI intelligence Chatbot to improve students learning in the higher education platform. J Interconnect Netw. 2022. https://doi.org/10.1142/s0219265921430325 .

Limna P. A Review of Artificial Intelligence (AI) in Education during the Digital Era. 2022. https://ssrn.com/abstract=4160798

Lo CK. What is the impact of ChatGPT on education? A rapid review of the literature. Educ Sci. 2023;13(4):410. https://doi.org/10.3390/educsci13040410 .

Luo W, He H, Liu J, Berson IR, Berson MJ, Zhou Y, Li H. Aladdin’s genie or pandora’s box For early childhood education? Experts chat on the roles, challenges, and developments of ChatGPT. Early Educ Dev. 2023. https://doi.org/10.1080/10409289.2023.2214181 .

Meyer JG, Urbanowicz RJ, Martin P, O’Connor K, Li R, Peng P, Moore JH. ChatGPT and large language models in academia: opportunities and challenges. Biodata Min. 2023. https://doi.org/10.1186/s13040-023-00339-9 .

Mhlanga D. Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4354422 .

Neumann, M., Rauschenberger, M., & Schön, E. M. (2023). “We Need To Talk About ChatGPT”: The Future of AI and Higher Education.‏ https://doi.org/10.1109/seeng59157.2023.00010

Nolan B. Here are the schools and colleges that have banned the use of ChatGPT over plagiarism and misinformation fears. Business Insider . 2023. https://www.businessinsider.com

O’Leary DE. An analysis of three chatbots: BlenderBot, ChatGPT and LaMDA. Int J Intell Syst Account, Financ Manag. 2023;30(1):41–54. https://doi.org/10.1002/isaf.1531 .

Okoli C. A guide to conducting a standalone systematic literature review. Commun Assoc Inf Syst. 2015. https://doi.org/10.17705/1cais.03743 .

OpenAI. (2023). https://openai.com/blog/chatgpt

Perkins M. Academic integrity considerations of AI large language models in the post-pandemic era: ChatGPT and beyond. J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.02.07 .

Plevris V, Papazafeiropoulos G, Rios AJ. Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard. arXiv (Cornell University) . 2023. https://doi.org/10.48550/arxiv.2305.18618

Rahman MM, Watanobe Y (2023) ChatGPT for education and research: opportunities, threats, and strategies. Appl Sci 13(9):5783. https://doi.org/10.3390/app13095783

Ram B, Verma P. Artificial intelligence AI-based Chatbot study of ChatGPT, google AI bard and baidu AI. World J Adv Eng Technol Sci. 2023;8(1):258–61. https://doi.org/10.30574/wjaets.2023.8.1.0045 .

Rasul T, Nair S, Kalendra D, Robin M, de Oliveira Santini F, Ladeira WJ, Heathcote L. The role of ChatGPT in higher education: benefits, challenges, and future research directions. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.29 .

Ratnam M, Sharm B, Tomer A. ChatGPT: educational artificial intelligence. Int J Adv Trends Comput Sci Eng. 2023;12(2):84–91. https://doi.org/10.30534/ijatcse/2023/091222023 .

Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst. 2023;3:121–54. https://doi.org/10.1016/j.iotcps.2023.04.003 .

Roumeliotis KI, Tselikas ND. ChatGPT and Open-AI models: a preliminary review. Future Internet. 2023;15(6):192. https://doi.org/10.3390/fi15060192 .

Rudolph J, Tan S, Tan S. War of the chatbots: Bard, Bing Chat, ChatGPT, Ernie and beyond. The new AI gold rush and its impact on higher education. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.23 .

Ruiz LMS, Moll-López S, Nuñez-Pérez A, Moraño J, Vega-Fleitas E. ChatGPT challenges blended learning methodologies in engineering education: a case study in mathematics. Appl Sci. 2023;13(10):6039. https://doi.org/10.3390/app13106039 .

Sallam M, Salim NA, Barakat M, Al-Tammemi AB. ChatGPT applications in medical, dental, pharmacy, and public health education: a descriptive study highlighting the advantages and limitations. Narra J. 2023;3(1): e103. https://doi.org/10.52225/narra.v3i1.103 .

Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care. 2023. https://doi.org/10.1186/s13054-023-04380-2 .

Saqr M, López-Pernas S, Helske S, Hrastinski S. The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: a full program study. Comput Educ. 2023;199:104787. https://doi.org/10.1016/j.compedu.2023.104787 .

Saqr M, Matcha W, Uzir N, Jovanović J, Gašević D, López-Pernas S. Transferring effective learning strategies across learning contexts matters: a study in problem-based learning. Australas J Educ Technol. 2023;39(3):9.

Schöbel S, Schmitt A, Benner D, Saqr M, Janson A, Leimeister JM. Charting the evolution and future of conversational agents: a research agenda along five waves and new frontiers. Inf Syst Front. 2023. https://doi.org/10.1007/s10796-023-10375-9 .

Shoufan A. Exploring students’ perceptions of CHATGPT: thematic analysis and follow-up survey. IEEE Access. 2023. https://doi.org/10.1109/access.2023.3268224 .

Sonderegger S, Seufert S. Chatbot-mediated learning: conceptual framework for the design of Chatbot use cases in education. Gallen: Institute for Educational Management and Technologies, University of St; 2022. https://doi.org/10.5220/0010999200003182 .

Book   Google Scholar  

Strzelecki A. To use or not to use ChatGPT in higher education? A study of students’ acceptance and use of technology. Interact Learn Environ. 2023. https://doi.org/10.1080/10494820.2023.2209881 .

Su J, Yang W. Unlocking the power of ChatGPT: a framework for applying generative AI in education. ECNU Rev Educ. 2023. https://doi.org/10.1177/20965311231168423 .

Sullivan M, Kelly A, McLaughlan P. ChatGPT in higher education: Considerations for academic integrity and student learning. J ApplLearn Teach. 2023;6(1):1–10. https://doi.org/10.37074/jalt.2023.6.1.17 .

Szabo A. ChatGPT is a breakthrough in science and education but fails a test in sports and exercise psychology. Balt J Sport Health Sci. 2023;1(128):25–40. https://doi.org/10.33607/bjshs.v127i4.1233 .

Taecharungroj V. “What can ChatGPT do?” analyzing early reactions to the innovative AI chatbot on Twitter. Big Data Cognit Comput. 2023;7(1):35. https://doi.org/10.3390/bdcc7010035 .

Tam S, Said RB. User preferences for ChatGPT-powered conversational interfaces versus traditional methods. Biomed Eng Soc. 2023. https://doi.org/10.58496/mjcsc/2023/004 .

Tedre M, Kahila J, Vartiainen H. (2023). Exploration on how co-designing with AI facilitates critical evaluation of ethics of AI in craft education. In: Langran E, Christensen P, Sanson J (Eds).  Proceedings of Society for Information Technology and Teacher Education International Conference . 2023. pp. 2289–2296.

Tlili A, Shehata B, Adarkwah MA, Bozkurt A, Hickey DT, Huang R, Agyemang B. What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learn Environ. 2023. https://doi.org/10.1186/s40561-023-00237-x .

Uddin SMJ, Albert A, Ovid A, Alsharef A. Leveraging CHATGPT to aid construction hazard recognition and support safety education and training. Sustainability. 2023;15(9):7121. https://doi.org/10.3390/su15097121 .

Valtonen T, López-Pernas S, Saqr M, Vartiainen H, Sointu E, Tedre M. The nature and building blocks of educational technology research. Comput Hum Behav. 2022;128:107123. https://doi.org/10.1016/j.chb.2021.107123 .

Vartiainen H, Tedre M. Using artificial intelligence in craft education: crafting with text-to-image generative models. Digit Creat. 2023;34(1):1–21. https://doi.org/10.1080/14626268.2023.2174557 .

Ventayen RJM. OpenAI ChatGPT generated results: similarity index of artificial intelligence-based contents. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4332664 .

Wagner MW, Ertl-Wagner BB. Accuracy of information and references using ChatGPT-3 for retrieval of clinical radiological information. Can Assoc Radiol J. 2023. https://doi.org/10.1177/08465371231171125 .

Wardat Y, Tashtoush MA, AlAli R, Jarrah AM. ChatGPT: a revolutionary tool for teaching and learning mathematics. Eurasia J Math, Sci Technol Educ. 2023;19(7):em2286. https://doi.org/10.29333/ejmste/13272 .

Webster J, Watson RT. Analyzing the past to prepare for the future: writing a literature review. Manag Inf Syst Quart. 2002;26(2):3.

Xiao Y, Watson ME. Guidance on conducting a systematic literature review. J Plan Educ Res. 2017;39(1):93–112. https://doi.org/10.1177/0739456x17723971 .

Yan D. Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11742-4 .

Yu H. Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching. Front Psychol. 2023;14:1181712. https://doi.org/10.3389/fpsyg.2023.1181712 .

Zhu C, Sun M, Luo J, Li T, Wang M. How to harness the potential of ChatGPT in education? Knowl Manag ELearn. 2023;15(2):133–52. https://doi.org/10.34105/j.kmel.2023.15.008 .

Download references

The paper is co-funded by the Academy of Finland (Suomen Akatemia) Research Council for Natural Sciences and Engineering for the project Towards precision education: Idiographic learning analytics (TOPEILA), Decision Number 350560.

Author information

Authors and affiliations.

School of Computing, University of Eastern Finland, 80100, Joensuu, Finland

Yazid Albadarin, Mohammed Saqr, Nicolas Pope & Markku Tukiainen

You can also search for this author in PubMed   Google Scholar

Contributions

YA contributed to the literature search, data analysis, discussion, and conclusion. Additionally, YA contributed to the manuscript’s writing, editing, and finalization. MS contributed to the study’s design, conceptualization, acquisition of funding, project administration, allocation of resources, supervision, validation, literature search, and analysis of results. Furthermore, MS contributed to the manuscript's writing, revising, and approving it in its finalized state. NP contributed to the results, and discussions, and provided supervision. NP also contributed to the writing process, revisions, and the final approval of the manuscript in its finalized state. MT contributed to the study's conceptualization, resource management, supervision, writing, revising the manuscript, and approving it.

Corresponding author

Correspondence to Yazid Albadarin .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

See Table  4

The process of synthesizing the data presented in Table  4 involved identifying the relevant studies through a search process of databases (ERIC, Scopus, Web of Knowledge, Dimensions.ai, and lens.org) using specific keywords "ChatGPT" and "education". Following this, inclusion/exclusion criteria were applied, and data extraction was performed using Creswell's [ 15 ] coding techniques to capture key information and identify common themes across the included studies.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Albadarin, Y., Saqr, M., Pope, N. et al. A systematic literature review of empirical research on ChatGPT in education. Discov Educ 3 , 60 (2024). https://doi.org/10.1007/s44217-024-00138-2

Download citation

Received : 22 October 2023

Accepted : 10 May 2024

Published : 26 May 2024

DOI : https://doi.org/10.1007/s44217-024-00138-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Large language models
• Educational technology
• Systematic review

Advertisement

• Find a journal
• Publish with us
• Track your research

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write a Paper with ChatGPT | Tips & Examples

How to Write a Paper with ChatGPT | Tips & Examples

Published on 17 August 2023 by Koen Driessen .

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarise and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarising or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyse the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organise your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?” The paper will be about 10 pages long.

B. Existing studies on cognitive and skill development benefits of virtual reality training

C. Comparison of virtual reality-based training with traditional training methods

D. Gaps in the literature and research limitations

III. Theoretical Framework

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question? “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organisations: Look for reports and publications from government agencies and non-profit organisations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

You can use ChatGPT to paraphrase or summarise text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialised tools featured on Scribbr’s AI writing resources page, which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialised tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarise text . This can help you understand complex information more easily, summarise the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summariser , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialised tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, having ChatGPT write your college essay can negatively impact your application in numerous ways. ChatGPT outputs are unoriginal and lack personal insight.

Furthermore, Passing off AI-generated text as your own work is considered academically dishonest . AI detectors may be used to detect this offense, and it’s highly unlikely that any university will accept you if you are caught submitting an AI-generated admission essay.

However, you can use ChatGPT to help write your college essay during the preparation and revision stages (e.g., for brainstorming ideas and generating feedback).

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Driessen, K. (2023, August 17). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved 26 May 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, ethical implications of chatgpt, still have questions.

What is ChatGPT?

• How to Use Google Gemini

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

ChatGPT: the latest news, controversies, and tips you need to know

ChatGPT has continued to dazzle the internet with AI-generated content, morphing from a novel chatbot into a piece of technology that is driving the next era of innovation. No tech product in recent memory has sparked as much interest, controversy, fear, and excitement.

How to use ChatGPT

How to use the chatgpt iphone and android apps, is chatgpt free to use, who created chatgpt, what do the chatgpt errors mean, latest chatgpt controversies, can chatgpt be detected, common uses for chatgpt, what are chatgpt plugins, is there a chatgpt api.

• What’s the future of ChatGPT and GPT-5?

ChatGPT alternatives worth trying

Other things to know about chatgpt.

If you’re just now catching on, it’d be fair to wonder what the fuss is all about. You can try it out for yourself for free (or use the official free iOS app ), but here’s the detailed guide you’ve been looking for — whether you’re worried about an AI apocalypse or are just looking for an intro guide to the app.

ChatGPT is a natural language AI chatbot . At its most basic level, that means you can ask it any question, and it will generate an answer.

Using the ChatGPT chatbot itself is fairly simple, as all you have to do is type in your text and receive information. The key here is to be creative and see how your ChatGPT responds to different prompts. If you don’t get the intended result, try tweaking your prompt or giving ChatGPT further instructions. ChatGPT knows the context of previous questions you ask, so you can refine from there rather than starting over fresh every time.

For example, starting with “Explain how the solar system was made” will give a more detailed result with more paragraphs than “How was the solar system made,” even though both inquiries will give fairly detailed results. Take it a step further by giving ChatGPT more guidance about style or tone, saying “Explain how the solar system was made as a middle school teacher.”

• ChatGPT not working? The most common problems and fixes
• Macs just got a huge AI boost
• The best ChatGPT plug-ins you can use

You also have the option for more specific inputting requests for an essay with a specific number of paragraphs or a Wikipedia page. We got an extremely detailed result with the request “write a four-paragraph essay explaining Mary Shelley’s Frankenstein.” And remember, ChatGPT is great at making tweaks to previous answers, so you can always ask for more detail, ask it to rewrite something, or ask it further questions.

To see what it can do, try using ChatGPT in daily life or work activities to see how it can help. Ask it to write emails, craft business proposals, fun date night ideas, or even a best man’s speech. So long as it doesn’t break some of the explicit or illegal content rules, the generator will do its best to fulfill the commands. It’s certainly is potential for ChatGPT to begin filling in gaps with incorrect data. As OpenAI notes, these instances are rare, but AI “hallucinations” certainly do happen . The company also notes that ChatGPT, which uses the GPT-3.5 LLM (large language model), currently has “limited knowledge of world events after 2021.” For more recent knowledge of the world, consider using another tool like Bing Chat .

However, OpenAI recently announced that ChatGPT Plus subscriber, who have access to the GPT-4 model, will be able to search the web for up-to-date information .

Even so, you have the option to input queries continuously until you close your browser or reset the thread to clear your previous requests. These chats are then saved in conversations in the sidebar, even automatically naming the chat. From there, you can manage these chats, renaming or deleting them as needed. You can even “hide” specific chats if needed .

You also have the option to use ChatGPT in dark mode or light mode.

Unlike Bing Chat , which can now generate images with Bing Image Creator and receive images as prompts for questions, ChatGPT only provides text outputs. In September 2023, however, OpenAI added the ability for you to use an image or voice as an input for your prompt. It’s currently only available to ChatGPT Plus subscribers.

As opposed to a simple voice assistant like Siri or Google Assistant , ChatGPT is built on what is called an LLM (Large Language Model). These neural networks are trained on huge quantities of information from the internet for deep learning — meaning they generate altogether new responses, rather than just regurgitating specific canned responses. They’re not built for a specific purpose like chatbots of the past — and they’re a whole lot smarter.

This is implied in the name of ChatGPT, which stands for Chat Generative Pre-trained Transformer. In the case of the current version of ChatGPT, it’s based on the GPT-3.5 LLM. The model behind ChatGPT was trained on all sorts of web content including websites, books, social media, news articles, and more — all fine-tuned in the language model by both supervised learning and RLHF (Reinforcement Learning From Human Feedback). OpenAI says this use of human AI trainers is really what makes ChatGPT stand out.

First, go to chat.openai.com . If it’s your first time, you’ll need to set up a free account with OpenAI before getting started. You have the option of choosing an easy login with a Google or Microsoft account, or just entering your email address. You’ll be asked next to enter a phone number ; however, keep in mind that you cannot use a virtual phone number (VoIP) to register for OpenAI. You will then receive a confirmation number, which you will enter on the registration page to complete the setup.

You’ll see some basic rules about ChatGPT, including potential errors in data, how OpenAI collects data, and how users can submit feedback — all of which have some wondering about whether or not ChatGPT is safe to use . Once you’re through that, you know you have successfully registered. You’re in!

After many months of anticipation, OpenAI has finally launched an official iOS app that you can go and download today . The app quickly topped half a million downloads in less than a week and is becoming available in an increasing number of countries .

Instructions for using it aren’t dissimilar to the ChatGPT web application. You do get an extra option for signing in using your Apple ID account, but it otherwise functions nearly identically to the web app — just type in your question and let the conversation begin.

The clean interface shows your conversation with GPT in a straightforward manner, hiding the chat history and settings behind the menu in the top right.

For those who are paying for ChatGPT Plus, the app lets you toggle between GPT-3.5 and GPT-4 too. You can even use the microphone to chat with ChatGPT over voice.

As our mobile editor noted in his experience with the app, it still doesn’t provide a connection to the internet like chatbots like Bing Chat and Perplexity .

Users have been asking for Android support for months, and now, a ChatGPT Android app is finally available . You can find it in the Google Play Store, but it’s limited to certain countries at the moment, including the U.S., India, and Brazil.

Some devices go beyond just the app, too. For instance, the Infinix Folax is an Android phone that integrated ChatGPT throughout the device. Instead of just an app, the phone replaces the typical smart assistant (Google Assistant) with ChatGPT.

Yes, the basic version of ChatGPT is completely free to use. There’s no limit to how much you can use ChatGPT in a day, though there is a word and character limit for responses .

It’s not free for OpenAI to continue running it, of course. Initial estimates are currently that OpenAI spends around $3 million per month to continue running ChatGPT, which is around $100,000 per day. A report from April indicated that the price of operation is closer to $700,000 per day .

Beyond the cost of the servers themselves, some egregious information has recently come out about what else has been done to train the language model against producing offensive content.

OpenAI also has a premium version of its chatbot, called ChatGPT Plus . It costs $20 a month but provides access even during peak times, faster responses, and first access to new features like GPT-4 .

ChatGPT was created by an organization called OpenAI, a San Francisco-based AI research lab. The organization started as a non-profit meant for collaboration with other institutions and researchers, funded by high-profile figures like Peter Thiel and Elon Musk.

OpenAI later became a for-profit company in 2019 and is now led by its CEO, Sam Altman. It runs on Microsoft’s Azure system infrastructure and is powered by Nvidia’s GPUs, including the new supercomputers just announced this year . Microsoft has invested heavily in OpenAI too, starting in 2019.

Many people attempting to use ChatGPT have been getting an “at capacity” notice when trying to access the site . It’s likely behind the move to try and use unofficial paid apps, which have already flooded app stores  and scammed thousands into paying for a free service.

Because of how much ChatGPT costs to run, it seems as if OpenAI has been limiting access when its servers are “at capacity.” It can take as long as a few hours to wait out, but if you’re patient, you’ll get through eventually. Of all the problems facing ChatGPT right now, this had been the biggest hurdle for keeping people from using it more. In some cases, demand has been so high that ChatGPT has gone down for several hours for maintenance multiple times over the past few months.

This seems to be less of a problem recently, though, as demand has normalized and OpenAI has learned to manage the traffic better, but in the middle of the day, it still makes an appearance from time to time.

Although ChatGPT is a very useful tool, it isn’t free of problems. It’s known for making mistakes or “hallucinations,” where it makes up an answer to something it doesn’t know. A simple example of how unreliable it can sometimes be involved misidentifying the prime minister of Japan .

Beyond just making mistakes, many people are concerned about what this human-like generative AI could mean for the future of the internet, so much so that thousands of tech leaders and prominent public figures have signed a petition to slow down the development. It was even banned in Italy due to privacy concerns, alongside complaints from the FTC — although that’s now been reversed. Since then, the FTC has reopened investigations against OpenAI on questions of personal consumer data is being handled.

Speaking of bans, a number of high-profile companies have been disallowing the use of ChatGPT internally, including Samsung, Amazon, Verizon, and even the United States Congress . Apple is also on the list, though Tim Cook stated that he uses it, just weeks after having it banned .

There’s also the concern that generative AI like ChatGPT could result in the loss of many jobs — as many as 300 million worldwide, according to Goldman Sachs. In particular, it’s taken the spotlight in Hollywood’s writer’s strike , which wants to ensure that AI-written scripts don’t take the jobs of working screenwriters.

Beyond that, multiple controversies have also sprung up around people using ChatGPT to handle tasks that should probably be handled by an actual person. One of the worst cases of this is generating malware, which the FBI recently warned ChatGPT is being used for.

For example, Vanderbilt University’s Peabody School was recently under fire for generating an email about a mass shooting and the importance of community. In addition, JPMorgan Chase is restricting the use of the AI chatbot for workers, especially for generating emails, which companies like Apple have also prohibited internally.

There are also privacy concerns. A recent GDPR complaint says that ChatGPT violates user’s privacy by stealing data from users without their knowledge, and using that data to train the AI model.

Lastly, ChatGPT was even made able to generate Windows 11 keys for free , according to one user. Of course, this is not how ChatGPT was meant to be used, but it’s significant that it was even able to be “tricked” into generating the keys in the first place.

Teachers, school administrators, and developers are already finding different ways around this and banning the use of ChatGPT in schools . Others are more optimistic about how ChatGPT might be used for teaching, but plagiarism is undoubtedly going to continue being an issue in terms of education in the future. There are some ideas about how ChatGPT could “watermark” its text and fix this plagiarism problem, but as of now, detecting ChatGPT is still incredibly difficult to do.

ChatGPT recently launched a new version of its own plagiarism detection tool , with hopes that it will squelch some of the criticism around how people are using the text generation. It uses a new feature called “AI text classifier,” which operates in a way familiar to other plagiarism software. According to OpenAI, however, the tool is still a work in progress and is “imperfect.”

Other tools like GPTZero claim to help detect ChatGPT plagiarism, too. Although they work, some extra editing on AI responses can still trip up these tools.

Well, that’s the fun part. Since its launch, people have been experimenting to discover everything the chatbot can and can’t do — and some of the results have been mind-blowing .

Learning the kinds of prompts and follow-up prompts that ChatGPT responds well to requires some experimentation though. Much like we’ve learned to get the information we want from traditional search engines, it can take some time to get the best results from ChatGPT. If you want to get started, we have a roundup of the best ChatGPT tips .

It really all depends on what you want out of it. To start out, try using it to write a template blog post, for example, or even blocks of code if you’re a programmer.

Our writers experimented with ChatGPT too, attempting to see if it could handle holiday shopping or even properly interpret astrological makeup . In both cases, we found limitations to what it could do while still being thoroughly impressed by the results.

But the fun is in trying it out yourself. Whether you think ChatGPT is an amazing piece of tech or will lead to the destruction of the internet as we know it, it’s worth trying out for yourself to see just what it’s capable of.

Following an update on August 10, you can now use custom instructions with ChatGPT . This allows you to customize how the AI chatbot responds to your inputs so you can tailor it for your needs.

You can’t ask anything, though. OpenAI has safeguards in place in order to “build a safe and beneficial artificial general intelligence.” That means any questions that are hateful, sexist, racist, or discriminatory in any way are generally off-limits.

The announcement of ChatGPT plugins caused a great stir in the developer community, with some calling it “the most powerful developer platform ever created.” AI enthusiasts have compared it to the surge of interest in the iOS App Store when it first launched, greatly expanding the capabilities of the iPhone.

Essentially, developers will be able to build plugins directly for ChatGPT, to open it up to have access to the whole of the internet and connect directly to the APIs of specific applications. It’s ChatGPT out in the real world. Some of the examples provided by OpenAI include applications being able to perform actions on behalf of the user, retrieve real-time information, and access knowledge-based information.

It’s currently only available on a waitlist, but early applications to use plugins with ChatGPT include Expedia, Instacart, Slack, and OpenTable — and now there are lots to explore, including the ones we’ve seen as the best ChatGPT plugins to try out.

Outside of the ChatGPT app itself, many apps had been announced as partners with OpenAI using the ChatGPT API. Of the initial batch, the most prominent example is Snapchat’s MyAI .

Essentially, this is a way for developers to access ChatGPT and plug its natural language capabilities directly into apps and websites. We’ve seen it used in all sorts of different cases, ranging from suggesting parts in Newegg’s PC builder to building out a travel itinerary with just a few words. Recently, OpenAI made the ChatGPT API available to everyone, and we’ve seen a surge in tools leveraging the technology, such as Discord’s Clyde chatbot or Wix’s website builder .

What’s the future of ChatGPT and GPT-5?

There’s no doubt that the tech world has become obsessed with ChatGPT right now, and it’s not slowing down anytime soon. GPT-4, the next iteration of the model, has officially launched, though it’s currently only available for ChatGPT Plus. We do know, however, that Bing Chat is at least partially built on the GPT-4 language model, even if certain elements such as visual input aren’t available.

But the bigger development will be how ChatGPT continues to be integrated into other applications. Microsoft reportedly made a multibillion-dollar investment in ChatGPT , which is already starting to pay off. The first integration was in Teams Premium , with some of OpenAI’s features showing up to automate tasks and provide transcripts. Most prominently, Microsoft revealed 365 Copilot , which integrates ChatGPT natural language prompts directly into Office apps like Word, PowerPoint, Outlook, and more.

There were initial reports that GPT-5 is on the way and could finish training later this year, with some people claiming that it would achieve AGI (artificial general intelligence). That’s a big, controversial statement, but clearly, things are progressing at a rapid pace.

Since then, OpenAI has stated that GPT-5 is not on the timeline and is not currently planned. That being said, the next version, GPT-4.5, is currently training and may be available later this year. OpenAI indicated that it may be done planning as early as September or October.

All that to say, if you think AI is a big deal now, just wait until it’s built into the most common applications that are used for work and school.

ChatGPT remains the most popular AI chatbot at the moment, but it’s not completely without competition. Microsoft’s Bing Chat is the biggest rival, which uses OpenAI’s GPT-4 model as a basis for its answers. Although it requires downloading the Edge browser to use, Bing Chat is free and offers some added features such as different writing modes, image creation, and search links. It even got a significant update recently that introduced features like export, third-party plugins, and multimodal support. There’s also YouChat, which uses GPT-3, an older model from OpenAI, and Forefront AI , which gives you access to GPT-4 and beyond.

The biggest non-GPT competitor to ChatGPT is Google Bard . It’s based on Google’s own homegrown language model, LaMDA, and Google seems intent on competing directly with OpenAI with Google Bard. The most recent updates make it a far more compelling alternative to ChatGPT , even if it’s not quite there.

There are a number of other chatbots out there, some of which are based on Meta’s open-source language model, LLaMA, such as Vicuna and HuggingChat .

Reports suggest Apple has been working on a ChatGPT rival for years , as well, though we haven’t seen it yet. Some reporters say it is “significantly behind competitors” at the moment.

Are ChatGPT chats private?

It depends on what you mean by private. All chats with ChatGPT are used by OpenAI to further tune the models, which can actually involve the use of human trainers. No, that doesn’t mean a human is looking through every question you ask ChatGPT, but there’s a reason OpenAI warns against providing any personal information to ChatGPT.

It should be noted that if you don’t delete your chats, the conversations will appear in the left sidebar. Unlike with other chatbots, individual chats within a conversation cannot be deleted, though they can be edited using the pencil icon that appears when you hover over a chat. When you delete the conversations, however, it’s not that ChatGPT forgets they ever happened — it’s just that they disappear from the sidebar chat history.

Fortunately, OpenAI has recently announced a way to make your chats hidden from the sidebar . These “hidden” chats won’t be used to train AI models either.

When was ChatGPT released?

ChatGPT was originally launched to the public in November of 2022 by OpenAI. The chatbot is based on the GPT-3.5 LLM, which is a fine-tuned version of GPT-3, a model first launched on March 15, 2022. GPT-3 itself, though, has been around for a few years now. It was first released in June 2020, but only as an autoregressive language model.

The predecessors to GPT-3 had very limited public exposure. GPT-2 was announced in February 2019, and the first research paper on GPT was published on OpenAI’s website in 2018.

Will ChatGPT replace Google Search?

Rather than replace it, chatbots are likely to be integrated directly into search. Microsoft has already done this with Bing Chat and Bing, which puts a “chat” tab right into the menu of Bing search.

Even Google has begun experimenting with integrating the smarts of Google Bard into search through its Search Generative Experience . We’re in the early days where all these exist as different products, but it’s not hard to imagine a future where it’s a completely unified experience.

Is Bing Chat the same as ChatGPT?

Microsoft has officially brought ChatGPT to Bing in the form of Bing Chat . After a long beta period, it was officially available to try out. But unlike ChatGPT , Bing Chat does require downloading the latest version of Edge. So Safari or Chrome users are out of luck.

In the early days of its release, Bing Chat was capable of some unhinged responses , but Microsoft has been quick to tame things a bit. It was recently announced that Bing Chat is using the latest GPT-4 language model , meaning it’s more powerful and accurate than ChatGPT . The new Edge Copilot mode also provides a more user-friendly way to get started, offering suggested prompts, links to learn more, and ways to tweak the kinds of answers it gives you. And now with the Windows Copilot , Bing Chat will live right on your desktop.

Is Google Bard the same as ChatGPT?

Unlike Bing Chat, Google Bard  uses an entirely different LLM to power its natural language capabilities. Upon its release, Bard has been using LaMDA, the company’s own model, which stands for Language Model for Dialogue Applications. As has been demonstrated from early on, Bard didn’t have quite the precision in its answers.

Reports indicate, however, that Bard is getting a massive update soon, going from being trained on 30 billion parameters up to 600 billion parameters. That could make it closer to what is possible with GPT-4.

Can you write essays with ChatGPT?

The use of ChatGPT has been full of controversy, with many onlookers considering how the power of AI will change everything from search engines to novel writing. It’s even demonstrated the ability to earn students surprisingly good grades in essay writing.

Essay writing for students is one of the most obvious examples of where ChatGPT could become a problem. ChatGPT might not write this article all that well, but it feels particularly easy to use for essay writing. Some generative AI tools, such as Caktus AI , are built specifically for this purpose.

Can ChatGPT write and debug code?

Absolutely — it’s one of the most powerful features of ChatGPT. As with everything with AI, you’ll want to double-check everything it produces, because it won’t always get your code right. But it’s certainly powerful at both writing code from scratch and debugging code.

Developers have used it to create websites, applications, and games from scratch — all of which are made more powerful with GPT-4, of course. There’s even a plug-in called ChatGPT Code Interpreter that makes programming with AI even more accessible.

What is the ChatGPT character limit?

OpenAI doesn’t set an exact character limit, but it will cut off around its responses at about 500 words or 4,000 characters. If you happen to give the chatbot a request for a specific number of words above 500, you might find that it cuts off mid-sentence somewhere after 500 words.

One way to get around this is just to ask it to “go on” or “continue,” but it depends on the prompt and type of response. Sometimes ChatGPT will more or less repeat the previous answers in different words.

The best way to get access to responses with longer characters is to upgrade to ChatGPT Plus.

Is there a ChatGPT bug bounty program?

Yes. A bug bounty program for ChatGPT was recently announced . The program was unveiled officially on OpenAI’s website , which details the types of “cash awards” that are being offered. They range from $200 to up to $20,000 for what it calls “exceptional discoveries.”

While addressing security researchers interested in getting involved in the program, OpenAI said it recognized “the critical importance of security and view it as a collaborative effort. By sharing your findings, you will play a crucial role in making our technology safer for everyone.”

Do you need to download ChatGPT?

ChatGPT is available via a webpage , so no downloading is needed. However, OpenAI has finally released a free, official iOS app that needs to be downloaded from the iOS app store. For many months, the various app stores were full of fake versions. These are still out there, though, and should be installed and used with caution, as they are not official ChatGPT apps. There is no still no official Android app.

On desktop, there are a couple of ways to install ChatGPT, though. First, you can navigate to the ChatGPT website and save it as a Windows app through Edge. Go to the site, click the ellipsis menu, and hover over Apps.  Select  Install this site as an app  to load ChatGPT from your desktop.

Other tools like MacGPT also allow shortcuts to access the browser service from your desktop.

Can you use ChatGPT on iPhone or Android?

Now that there’s an official iOS app, you no longer have to rely solely on the web app to use ChatGPT on your phone . So, whether with the official app as downloaded through the app store or just the web version, you can certainly use ChatGPT on iPhones. In addition, there’s even a way to replace Siri with ChatGPT on your iPhone, as well as some useful mobile apps like Perplexity AI .

As for Android, you’ll need to rely on the web app. Just as on desktop, type in chat.openai.com to start using ChatGPT.

Can you get ChatGPT to answer any question?

Not exactly. ChatGPT has limitations in the kinds of questions it can answer. First of all, it can’t write about anything that requires internet knowledge after late 2021, which is when its training stopped.

Beyond that, ChatGPT is careful about answering questions that might imply illegal, explicit, or damaging activity. It’ll avoid swearing or political debates, and will (usually) avoid making malware. There is some amount of jailbreaking that can be done to get around these restrictions, but OpenAI is constantly tightening its content policies to restrict unwanted answers. One example of a common jailbreaking technique is the DAN (Do Anything Now) prompt , though OpenAI has worked hard to plug these holes over time.

What is Auto-GPT?

Built on GPT-4, Auto-GPT is the latest evolution of AI technology to cause a stir in the industry. It’s not directly related to ChatGPT or OpenAI — instead, it’s an open-source Python application that got into the hands of developers all over the internet when it was published on GitHub .

With ChatGPT or ChatGPT Plus, the capabilities of the AI are limited to a single chat window. Auto-GPT, at its simplest, is making AI autonomous. It can be given a set of goals, and then take the necessary steps towards accomplishing that goal across the internet, including connecting up with applications and software.

According to the official description on GitHub, Auto-GPT is an “experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM ‘thoughts’, to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.”

The demo used on the GitHub page is simple — just create a recipe appropriate for Easter and save it to a file. What’s neat is how Auto-GPT breaks down the steps the AI is taking to accomplish the goal, including the “thoughts” and “reasoning” behind its actions. Auto-GPT is already being used in a variety of different applications, with some touting it as the beginning of AGI (Artificial General Intelligence) due to its autonomous nature.

What is GPT-4 and how does it compare to GPT-3.5?

GPT-4 is a more advanced LLM — the most powerful that OpenAI currently offers. At the current moment, OpenAI only offers access to GPT-4 through ChatGPT Plus. GPT-3.5, on the other hand, is the LLM that powers the free ChatGPT tool. OpenAI no longer says exactly how many parameters these advanced models are trained on, but it’s rumored that GPT-4 boasts up to 1 trillion parameters.

Regardless, the results are a fairly dramatic difference between GPT-3.5 and GPT-4 in terms of quality. It offers much more precise answers, is significantly better at coding and creative collaboration, and can provide (and respond to) much longer selections of text. GPT-4 remains the best possible model available, while GPT-3.5 is more in line with some other models available.

Who owns the copyright to content created by ChatGPT?

This is a question open to debate. Much of the conversation around copyright and AI is ongoing, with some saying generative AI is “stealing” the work of the content it was trained on. This has become increasingly contentious in the world of AI art. Companies like Adobe are finding ways around this by only training models on stock image libraries that already have proper artist credit and legal boundaries.

According to OpenAI, however, you have the right to reprint, sell, and merchandise anything that was created with ChatGPT or ChatGPT Plus. So, you’re not going to get sued by OpenAI.

The larger topic of copyright law regarding generative AI is still to be determined by various lawmakers and interpreters of the law, especially since copyright law as it currently stands technically only protects content created by human beings.

Editors' Recommendations

• OpenAI strikes major deal with News Corp to boost ChatGPT
• GPT-4o: What the latest ChatGPT update can do and when you can get it
• ChatGPT can laugh now, and it’s downright creepy
• Apple finally has a way to defeat ChatGPT
• GPT-4 vs. GPT-3.5: how much difference is there?
• Artificial Intelligence

ChatGPT, the AI-powered chatbot that went viral at the start of last year and kicked off a wave of interest in generative AI tools, no longer requires an account to use.

Its creator, OpenAI, launched a webpage on Monday that lets you begin a conversation with the chatbot without having to sign up or log in first.

In recent years, the listening time required by a piece of AI to clone someone’s voice has been getting shorter and shorter.

It used to be minutes, now it’s just seconds.

It looks like OpenAI's ChatGPT and Sora, among other projects, are about to get a lot more juice. According to a new report shared by The Information, Microsoft and OpenAI are working on a new data center project, one part of which will be a massive AI supercomputer dubbed "Stargate." Microsoft is said to be footing the bill, and the cost is astronomical as the name of the supercomputer suggests -- the whole project might cost over $100 billion.

Spending over $100 billion on anything is mind-blowing, but when put into perspective, the price truly shows just how big a venture this might be: The Information claims that the new Microsoft and OpenAI joint project might cost a whopping 100 times more than some of the largest data centers currently in operation.

Home — Blog — AI Hacks and Tips — How to Cite ChatGPT: Popular Citation Styles with Examples

How to Cite ChatGPT: Popular Citation Styles with Examples

Artificial Intelligence (AI) is rapidly transforming various aspects of our lives, including education. Tools like ChatGPT are becoming increasingly popular among students for generating ideas, answering questions, and even drafting parts of assignments. However, as with any source of information, it's crucial to how to cite ChatGPT to maintain academic integrity and avoid plagiarism. This article will guide you through the process of citing ChatGPT, ensuring you adhere to ethical standards and give credit where it's due.

Why Cite ChatGPT?

Ethical Considerations: Using AI tools like ChatGPT in your academic work comes with ethical responsibilities. Proper citation is not just about following rules; it's about respecting the intellectual contributions of others, even if they are generated by a machine. By citing ChatGPT, you acknowledge the source of your information and contribute to a culture of honesty and integrity in academia.

Avoiding Plagiarism: Plagiarism is a serious academic offense that can have severe consequences. It involves presenting someone else's work or ideas as your own without proper acknowledgment. When you use ChatGPT to generate content, failing to cite it appropriately can be considered plagiarism. Proper citation helps you avoid this pitfall by clearly indicating which parts of your work were assisted by AI.

Acknowledging Sources: Just as you would cite a book, article, or website, citing ChatGPT is a way to acknowledge the tools and resources that contributed to your work. This not only adds credibility to your work but also helps others understand the origins of your ideas and findings.

General Guidelines for Citing AI Tools

Citing AI tools like ChatGPT is slightly different from citing traditional sources. Here are some general guidelines to follow:

• Identify the Tool: Clearly mention that you used ChatGPT, specifying the version if possible.
• Include the Source: Indicate that the tool is developed by OpenAI.
• Mention the Date: Provide the date when you accessed or generated the content using ChatGPT.
• Detail the Interaction: Briefly describe how you used ChatGPT in your work.

These elements ensure that your citation is clear and comprehensive, giving proper credit to the AI tool.

How to Cite Chat GPT as a Source : Citation Styles

Different academic disciplines follow different citation styles, and it's important to understand how to properly cite ChatGPT to maintain academic integrity. Here’s a guide on ChatGPT citation in the most commonly used styles: APA, MLA, and Chicago. Each style has specific guidelines for citing sources, including AI tools like ChatGPT. By following these guidelines, you can ensure that you properly credit ChatGPT as a source in your academic work, thereby avoiding plagiarism and adhering to the ethical standards of your discipline. Let's explore how to cite ChatGPT in each of these citation styles.

How to Cite ChatGPT in APA

When learning how to cite AI in APA, it's essential to include all the necessary details to ensure your citation is complete and accurate. In APA style, the citation for ChatGPT should include the author, which is OpenAI, the year of publication, the name of the tool, and a retrieval statement that includes the URL. Properly citing AI tools like ChatGPT is crucial for maintaining academic integrity and giving appropriate credit to the sources that contribute to your work. Here’s an example to guide you on how to cite ChatGPT in APA style:

• Author : OpenAI
• Year : 2023
• Tool's Name: ChatGPT
• Version: May 24 version
• Retrieval Statement: URL where the tool can be accessed

How to Cite ChatGPT in MLA

When formatting a ChatGPT citation in MLA style, it’s important to include specific details to ensure your citation is complete and accurate. In MLA style, the citation should mention the author, which is OpenAI, the name of the tool, the publisher, and the date of access. Proper citation of AI tools like ChatGPT is essential for maintaining academic integrity and providing clear acknowledgment of the sources used in your work. Here’s how to cite ChatGPT in MLA style:

• Author: OpenAI
• Publisher: OpenAI
• Date of Access: 24 May 2023
• URL: The link to the tool

Chicago Style ChatGPT Citation

When citing ChatGPT in Chicago style, the citation can be included either in a footnote or in a bibliography. Properly citing ChatGPT is essential to maintaining academic integrity and ensuring that the contributions of AI tools are appropriately credited. Here’s how you can format a citing ChatGPT entry in Chicago style:

Example (footnote):

Example (bibliography):

• Date: May 24, 2023

Citing ChatGPT: P ractical Tips for Students

You should cite ChatGPT whenever you use it to generate significant content, ideas, or data that contribute to your work. This includes direct quotes, paraphrased information, and any substantial assistance in shaping your arguments or research.

How to integrate AI-generated content into your work:

• Direct Quotes: Use quotation marks and a citation when directly quoting text generated by ChatGPT.
• Paraphrasing: Even when paraphrasing, you must still provide a citation.
• Summarizing: If you summarize information from ChatGPT, make sure to cite it.

Best practices for using AI tools in academic writing:

• Verify Information: Always cross-check the information generated by AI tools for accuracy.
• Use Responsibly: AI should complement your own research and writing efforts, not replace them.
• Understand Limitations: Be aware of the limitations and potential biases in AI-generated content.

Common Mistakes to Avoid

Misrepresenting AI-Generated Content as Original Thought: Always clarify which parts of your work were assisted by AI to avoid giving a false impression of originality.

Incomplete or Incorrect Citations: Ensure your citations are complete and follow the correct format for your citation style. Incomplete or incorrect citations can lead to confusion and reduce the credibility of your work.

Over-Reliance on AI Tools: While AI tools are helpful, relying too heavily on them can undermine your learning and critical thinking skills. Use them as a supplement to your efforts, not a substitute.

Understanding how to cite ChatGPT and other AI tools is crucial for maintaining academic integrity and avoiding plagiarism. Proper citation not only acknowledges the use of these advanced technologies but also upholds the standards of ethical academic practices. By following the guidelines and examples provided in this article, you can ensure that you properly credit the contributions of AI in your work. This includes understanding how to cite ChatGPT in different citation styles such as APA, MLA, and Chicago. Remember to use these tools responsibly, verify the information they provide, and integrate their contributions transparently into your research. Happy writing!

We use cookies to personalyze your web-site experience. By continuing we’ll assume you board with our cookie policy .