how to get literature review from chatgpt

How To Use ChatGPT To Write A Literature Review: Prompts & References

In the rapidly evolving world of academic research, the integration of AI tools like ChatGPT has transformed the traditional approach to literature reviews. As a researcher, you should also leverage on this tool to make your research work easier.

In this post, explore how ChatGPT can enhance the literature review process. We’ll explore how specific prompts can effectively guide this advanced AI model to generate insightful content, while ensuring accuracy, relevance, and academic integrity in their scholarly work.

How to Use ChatGPT for Writing a Literature Review

Understanding chatgpt’s limitations.

While it can efficiently generate content, streamline the research process, and provide a comprehensive understanding of relevant literature, its capabilities are not without constraints. Here are some for you to consider:

Dependence On Pre-Existing Datasets

Since ChatGPT is a language model trained on available data, it may not include the most recent research papers or cutting-edge findings in a specific field. This gap can lead to a lack of current state-of-research insights, particularly crucial in fields like technology and science where advancements happen rapidly.

May Lack Depth And Context

ChatGPT, while able to produce summaries and synthesize information, might not fully grasp the nuanced arguments or complex theories specific to a research topic. This limitation necessitates that researchers critically evaluate and supplement AI-generated text with thorough analysis and insights from recent systematic reviews and primary sources.

Risk Of Plagiarism

Although ChatGPT can generate human-like text, it’s vital to ensure that the content for your literature review is original and properly cited. Relying solely on ChatGPT to write a literature review defeats the purpose of engaging deeply with the material and developing a personal understanding of the literature.

Not A Total Replacement of A Researcher

While ChatGPT can assist non-native English speakers in crafting clear and concise academic writing, it’s not a replacement for the human ability to contextualize and interpret research findings. Researchers must guide the AI model with specific prompts and leverage it as a tool rather than a substitute for comprehensive analysis.

By keeping these limitations in mind, ChatGPT can be a valuable aid in the literature review process, but it should be used judiciously and in conjunction with traditional research methods.

Defining Research Objective

When starting on writing a literature review, the initial step involves using ChatGPT to define your research question or hypothesis.

The AI model’s ability to respond with a summary of the current state of research in your field can provide a comprehensive understanding, especially for systematic reviews or research papers.

For example, by inputting a prompt related to your research topic, ChatGPT can generate human-like text, summarizing prior research and highlighting relevant literature.

One insider tip for effectively using ChatGPT in the literature review process is to leverage its natural language processing capabilities to identify relevant keywords.

These keywords are crucial for non-native English speakers or those new to a research field, as they streamline the search for pertinent academic writing. Additionally, ChatGPT can guide you in understanding the context of your research topic, offering insights that are often challenging to find.

Using AI language models like ChatGPT for generating content for your literature review is efficient and effective, saving valuable time. However, it’s vital to critically evaluate the generated text to ensure it aligns with your research objectives and to avoid plagiarism.

how to get literature review from chatgpt

ChatGPT’s ability to synthesize large amounts of information can aid in developing a clear and concise outline, but remember, it’s a guide, not a replacement for human analysis.

Despite these limitations, ChatGPT provides a unique advantage in conducting literature reviews. It can automate mundane tasks, allowing researchers to focus on analysis and critical thinking.

Identifying Keywords and Search Terms

Using ChatGPT to identify relevant keywords related to your research topic can significantly streamline your workflow.

For instance, when you input a summary of your research question into ChatGPT, the AI model can generate a list of pertinent keywords.

These keywords are not just randomly selected; they are based on the vast amounts of information in ChatGPT’s dataset, making them highly relevant and often inclusive of terms that are current in your research field.

An insider tip for leveraging ChatGPT effectively is to guide the AI with clear and concise prompts.

For example, asking ChatGPT to: “summarize key themes in [specific field] research papers from the last five years” can yield a list of keywords and phrases that are not only relevant but also reflective of the current state of research.

This approach is particularly beneficial for conducting systematic reviews or for non-native English speakers who might be unfamiliar with specific academic jargon.

While ChatGPT can provide a comprehensive understanding of relevant literature and help automate the identification of keywords, it’s important to critically evaluate the generated content.

Researchers should use ChatGPT as a tool to augment their research process, not as a replacement for human insight.

It’s crucial to mind the limitations of the AI model and ensure that the keywords identified align with the research topic and objectives.

Creating an Initial Literature Review Outline

The key to using ChatGPT effectively in crafting an initial outline lies in its ability to generate content based on specific prompts.

For instance, a researcher working on organic photovoltaic devices can input a prompt into ChatGPT, such as “Help me create a structure for a literature review on organic photovoltaic devices.”

The AI model, using its comprehensive understanding of the research topic, can then produce a preliminary structure, including sections like:

Introduction
Advances in materials and technology, performance, and efficiency.

This generated outline serves as a valuable starting point. It helps in organizing thoughts and determining the key areas that the literature review should cover. I

mportantly, researchers can refine and expand this initial outline as they delve deeper into their topic, ensuring it aligns with their specific research question and the current state of research.

However, while ChatGPT can streamline the review process and save valuable time in creating an initial outline, researchers should not solely rely on it.

The content generated by ChatGPT must be critically evaluated and supplemented with in-depth research. This involves:

Reading systematic reviews
Reading research papers, and
Summarizing relevant literature to ensure the review is comprehensive and up-to-date.

Get ChatGPT To Help You During Research, Using The Right Prompts

The key to effectively using ChatGPT in this process lies in crafting the right prompts, guiding the AI to generate relevant and useful content.

When initiating a literature review, the prompt should aim for a broad understanding of the research topic. For instance, asking ChatGPT to:

“Give a brief overview of research done on [topic]”
“What are some of the recent findings on the [topic] in research?” or
“Summarize the historical development of [topic] in academia”

Helps in capturing the general landscape of the field. These prompts assist in identifying key theories, methodologies, and authors within the research area. As the review progresses, more specific prompts are necessary to delve deeper into individual studies. Queries like:

“Summarize the main arguments and findings of [specific paper]” or
“What are the strengths and weaknesses of [specific paper]?”

enable ChatGPT to provide detailed insights into particular research papers, aiding in understanding their contribution to the broader field. Comparative prompts are also crucial in synthesizing information across multiple works. Asking ChatGPT to:

“Compare and contrast the methodologies of [paper 1] and [paper 2]” or
“How do the findings of [paper 1] and [paper 2] agree or disagree?”

helps in discerning the nuances and disparities in the literature. In the final stages of the literature review, prompts should focus on summarizing findings and identifying emerging trends or gaps. For example:

“What trends or patterns have emerged from the literature on [topic]?” or
“What future research directions are suggested by the literature on [topic]?”

We will share more on these ChatGPT prompts in the later part of this post, read on.

Reviewing ChatGPT’s Responses

When using ChatGPT to write a literature review, it’s crucial to critically evaluate its responses.

Firstly, researchers should cross-reference the information provided by ChatGPT with actual research papers.

This step ensures the accuracy of the data and helps in identifying any discrepancies or outdated information, given that ChatGPT’s dataset may not include the most recent studies.

Another essential aspect is assessing the coherence and depth of the AI-generated text. ChatGPT can summarize and synthesize information efficiently, but it might not capture the nuances of complex theories or research arguments.

Researchers should ensure that the content aligns with their research question and systematically reviews the topic comprehensively. This is where a researcher’s value comes in.

Additionally, verifying the originality of the content is vital to avoid plagiarism. While ChatGPT can generate human-like text, researchers must ensure that the AI-generated content is used as a guide rather than a verbatim source.

Proper citations and references are essential to maintain the integrity of the literature review. Avoid torpedoing your own research by committing plagiarism.

Ensuring Coherence and Flow

One of the challenges when using such advanced AI language models is ensuring the coherence and flow of the final document. This aspect is crucial as it determines the readability and academic rigor of the literature review.

ChatGPT can generate vast amounts of content on a wide range of topics, responding efficiently to prompts and synthesizing information from its extensive dataset.

However, the content generated by ChatGPT, while informative, might not always align seamlessly with the specific research question or maintain a consistent narrative flow.

To tackle this, researchers need to take an active role in guiding ChatGPT and subsequently refining its output.

A practical approach is to use ChatGPT as a starting point, leveraging its ability to quickly provide summaries, synthesize relevant literature, and identify key references and keywords related to the research topic. For example, prompts like:

“Summarize the current research on [topic]” or
“Identify key debates in [topic]”

Can yield valuable initial insights.

Once this foundational information is obtained, the crucial task is to carefully review and edit the AI-generated content.

This involves connecting the dots between different sections, ensuring that each part contributes meaningfully to addressing the research question, and refining the language to maintain academic standards.

It’s also essential to check for and avoid plagiarism, ensuring that all sources are correctly cited.

In addition, considering the vast amounts of information ChatGPT can access, it’s vital to verify the accuracy and relevance of the content.

Researchers should cross-reference AI-generated summaries with actual research papers, especially the most recent ones, as ChatGPT’s dataset may not include the latest studies.

Editing and Proofreading

Now that your literature review is mostly written out, now focus on the editing and proofreading. The content generated by ChatGPT needs to be meticulously reviewed and edited. Here are the steps:

Verifying the accuracy of the information. Researchers must cross-check the AI-generated content against actual research papers and systematic reviews. This ensures that the latest studies are accurately represented.
Improve coherence and flow. Researchers should restructure sentences, ensure logical progression of ideas, and maintain a consistent academic tone throughout the document.
Checking for plagiarism. Despite ChatGPT’s ability to generate human-like text, researchers must ensure that all sources are correctly cited and that the review does not inadvertently replicate existing material.
Check Grammar and Spelling: Editing should encompass grammar checks, vocabulary refinement, and ensuring that the language used is appropriate for an academic audience.
Update Citation: Review citation, or reference list to ensure everything is cited correctly, and the citation list is written out to your required standard, be it MLA, Chicago, or APA.

What ChatGPT Prompts To Use When Writing A Literature Review?

There are many ways to use ChatGPT to write literature review, usually by using the right prompts. Here’s how specific types of prompts can be effectively employed, with multiple examples for each category:

“Provide a comprehensive overview of the latest research on [topic].”
“Summarize the current understanding and key findings in the field of [topic].”
“Detail the dominant theoretical frameworks currently used in [topic].”
“Describe the evolution of theoretical approaches in [topic] over the past decade.”
“Identify and discuss the major debates or controversies in [topic].”
“What are the conflicting viewpoints or schools of thought in [topic]?”
“List the leading researchers in [topic] and summarize their key contributions.”
“Who are the emerging authors in [topic], and what unique perspectives do they offer?”
“Explain the most common research methodologies used in studies about [topic].”
“How have the methodologies in [topic] research evolved recently?”
“Trace the historical development and major milestones in [topic].”
“Provide a timeline of the key discoveries and shifts in understanding in [topic].”
“What significant paradigm shifts have occurred in [topic] in the last twenty years?”
“How has the focus of research in [topic] changed over time?”
“Analyze the methodology and conclusions of [specific paper].”
“Discuss the impact and reception of [specific paper] in the field of [topic].”
“Compare the results and methodologies of [paper 1] and [paper 2] in [topic].”
“How do [paper 1] and [paper 2] differ in their approach to [topic]?”
“Based on current literature, what are the suggested future research directions in [topic]?”
“Identify gaps in the literature of [topic] that could be explored in future studies.”

By using these types of prompts, researchers can guide ChatGPT to produce content that is not only relevant to their literature review but also rich in detail and scope.

Wrapping Up: Use Other AI Tools Too, Not Just ChatGPT

In conclusion, while ChatGPT serves as a powerful ally in the literature review process, it’s important to recognize it as one of many AI tools available to researchers as well. Diversifying your AI toolkit can enhance the depth and breadth of your review, offering varied perspectives and methodologies.

As AI continues to evolve, embracing a range of these tools can lead to more comprehensive, nuanced, and innovative academic writing, expanding the horizons of research and scholarly exploration beyond what we currently envision.

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

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
J Pediatr Pharmacol Ther
v.28(6); 2023
PMC10731938

ChatGPT for Research and Publication: A Step-by-Step Guide

Som s. biswas.

Department of Pediatric Radiology, Le Bonheur Children’s Hospital, The University of Tennessee Health Science Center, Memphis, TN.

Introduction

This commentary provides a concise step-by-step guide on using ChatGPT, an advanced natural language processing (NLP) model, for research and publication purposes. The guide assesses crucial aspects, including data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations. By addressing challenges related to biases, interpretability, and plagiarism, this commentary offers insights and recommendations for the responsible and ethical use of ChatGPT. The guide empowers researchers to ethically integrate ChatGPT effectively into their workflows, enhancing productivity and improving the quality of their scientific publications. Through clear instructions and guidelines, researchers can tap into the transformative potential of ChatGPT, driving scientific progress in a language-driven world.

In recent years, the field of NLP has witnessed remarkable advancements, bringing us closer to the realm of humanlike language generation. Among these advancements, ChatGPT, based on the groundbreaking GPT-3.5 architecture developed by OpenAI, stands as an impressive language model capable of generating coherent and contextually relevant text responses. With its ability to understand and respond to user inputs, ChatGPT has opened up new possibilities for various applications, including research and publication. 1 – 3

The traditional process of conducting research and publishing scientific papers has been significantly transformed by the emergence of ChatGPT. Researchers and authors can now leverage the power of this sophisticated language model to streamline and enhance their workflow, leading to improved efficiency and higher-quality publications. However, using ChatGPT effectively in the research and publication domain requires a comprehensive understanding of its capabilities, limitations, and best practices.

In this commentary I offer my thoughts for a step-by-step guide for researchers and authors who seek to harness the potential of ChatGPT in their research endeavors and publication efforts. By exploring various aspects, such as data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations, this guide will equip researchers with the necessary knowledge to harness the full potential of ChatGPT in their scientific pursuits. Moreover, this commentary will delve into the challenges associated with using ChatGPT for research and publication, including biases, interpretability, and concerns regarding plagiarism. By addressing these challenges directly, I aim to provide researchers with valuable insights and recommendations to navigate these important issues and ensure the responsible and ethical use of ChatGPT as a research tool. 4

The significance of my guide lies in its potential to bridge the gap between the rapid progress of language models like ChatGPT and the research and publication process. By elucidating the intricacies of integrating ChatGPT into scientific workflows, researchers will be empowered to leverage this advanced technology effectively, thereby enhancing the overall quality and impact of their research output. 5 In the following sections, I present a comprehensive overview of the steps involved in using ChatGPT for research and publication.

Step 1: Title and Title Page Creation by ChatGPT

ChatGPT can be a valuable tool in generating titles for research papers. Its ability to understand and generate humanlike text allows it to analyze and synthesize information provided by researchers to craft concise and impactful titles. By leveraging its vast knowledge base and language capabilities, ChatGPT can assist in capturing the essence of a research paper, conveying the main focus and contributions succinctly. Researchers can collaborate with ChatGPT by providing relevant information, such as the subject, objectives, methodology, and key findings of their study. ChatGPT can then generate multiple title options, offering different perspectives and angles that researchers can consider. This collaboration with ChatGPT can save time and stimulate creativity, helping researchers refine their titles to accurately represent their work and engage potential readers. ChatGPT can then be used to create the entire title page and then can also customize based on each journal’s recommendations.

For example:

An external file that holds a picture, illustration, etc.
Object name is i2331-348X-28-6-576-f01.jpg

Thus, we see that ChatGPT can write an entire title page based on just the title and author details. We notice that ChatGPT has created an email address that is incorrect and needs manual rectification. However, the rest of the title page, including keywords and the running title, is appropriate.

Step 2: Abstract/Summary Creation by chatGPT

ChatGPT can assist in condensing complex information into a clear and engaging abstract/summary, helping researchers communicate the significance and novelty of their research to a wider audience. By leveraging the language proficiency of ChatGPT, researchers can save time and effort in crafting abstracts while ensuring that the key aspects of their study are accurately represented.

In this example, we demonstrate that ChatGPT can create an entire abstract just by using the title alone. However, the more information researchers provide (preferably the entire body of the paper should be entered into chatGPT), the more accurate the abstract becomes.

An external file that holds a picture, illustration, etc.
Object name is i2331-348X-28-6-576-f02.jpg

Step 3: Introduction Creation by ChatGPT

By collaborating with ChatGPT, researchers can provide key information, such as the background, significance, and objectives of their study. ChatGPT can then generate a well-structured introduction that sets the context, highlights the relevance of the research, and outlines the paper’s objectives. Also, ChatGPT can be used to generate keywords and generate an abbreviations list from the article by using prompts. However, it is important to note that the generated introduction should be reviewed, customized, and refined by the researchers to align with their specific study and writing style.

In the example below, we note that ChatGPT has not only created an introduction but also the objectives of the study, which can then be edited by the human author.

An external file that holds a picture, illustration, etc.
Object name is i2331-348X-28-6-576-f03.jpg

Step 4: Can ChatGPT Create a Literature Review?

Yes, ChatGPT can help generate a literature review, but it is important to note that it may not have access to the most up-to-date research articles and studies due to copyrights and limited access to some journals. Additionally, a literature review typically requires a comprehensive analysis of multiple sources, so the generated response may not cover all relevant studies. Nonetheless, it can assist in providing a basic literature review on a given topic, which will need human authors to add to and edit it.

An external file that holds a picture, illustration, etc.
Object name is i2331-348X-28-6-576-f04.jpg

As we can see, ChatGPT is not as good at giving a detailed review of the literature as it is at summarizing contents or creating an introduction. Thus, its use is limited, if there is any at all, in this section of the paper.

Step 5: Can ChatGPT Assist in Brainstorming the Methodology of Studies?

ChatGPT can be a helpful tool in conceptualizing the methodology for research papers. By engaging in a conversation with ChatGPT, researchers can discuss their research objectives, study design, data collection methods, and data analysis techniques. ChatGPT’s natural language understanding allows it to provide suggestions and insights based on its knowledge base and understanding of research methodologies. Although ChatGPT can assist in generating ideas and providing guidance, it is important for researchers to critically evaluate and adapt the suggestions to align with their specific research goals and requirements.

Although the methodology is something that is unique to each paper and needs a human researcher to conceptualize it, we see in this example that ChatGPT can assist by giving ideas and examples based on the input of the title by the human researcher. Thus, ChatGPT can be part of brainstorming sessions when conceptualizing a study, although this section needs significant editing by a human, unlike the introduction or summary.

An external file that holds a picture, illustration, etc.
Object name is i2331-348X-28-6-576-f05.jpg

Step 6: Do Not Use ChatGPT for Fabricating Patient Data or Results!

This section of the paper must be authentic, and ChatGPT has a limited role, if any, because patient data have to be original. ChatGPT also currently cannot analyze clinical data compared with statistical software, like SPSS Statistics and Base SAS. However, Microsoft appears to be developing an Excel copilot that uses AI to create graphs and plots, and its use needs to be evaluated once it is released to the public. 6

Step 7: Discussion and Conclusions

This section of the paper can be generated by ChatGPT if all results are pasted as input; however, this section also needs manual editing because inaccuracies are common. By discussing their research with ChatGPT, researchers can also identify potential limitations, discuss the broader implications of their findings, and propose future research directions. Although ChatGPT can generate suggestions and facilitate the thought process, it is important for researchers to critically evaluate the information provided and ensure that the Discussion and Conclusion sections align with the specific research objectives and findings of their study. Ultimately, ChatGPT can serve as a supportive tool in developing a comprehensive and well-rounded discussion and conclusion for research papers.

Step 8: References

As per the author's experience, although ChatGPT is capable of creating references for an article, most of them are incorrect. So, using ChatGPT for creating references is not recommended. However, ChatGPT can convert references into any journaling style if the references are entered into ChatGPT and it is asked to convert them into a specific style.

Disadvantages of Using ChatGPT in Research

Although ChatGPT offers numerous advantages for assisting in the writing of research papers, there are also some important potential disadvantages to consider:

Lack of domain expertise: ChatGPT is a general-purpose language model trained on a diverse range of Internet text, which means it may lack the specific domain expertise required for certain research topics. It may generate responses that are not accurate or well informed in specialized fields, potentially leading to incorrect or misleading information in research papers.
Inconsistency and variability: ChatGPT’s responses can be inconsistent and vary depending on the input phrasing or prompt formulation. This can lead to unpredictability in generating reliable and coherent content, requiring additional effort to refine and ensure accuracy in research papers.
Limited control over output: Although researchers can guide the model’s responses through prompts, ChatGPT’s generation process is still primarily autonomous. Researchers have limited control over the precise content and structure of the generated text, which may require careful editing and review to align with specific research goals, standards, and above all, accuracy.
Biases and ethical considerations: Language models like ChatGPT can inadvertently reflect biases present in the training data. These biases may perpetuate existing societal or cultural biases in research papers, potentially leading to unfair or discriminatory content. The careful examination and mitigation of biases are crucial to ensure ethical and unbiased research output. 7
Lack of interpretability: ChatGPT’s decision-making process is complex and not easily interpretable. Researchers may struggle to understand the reasoning behind the model’s generated responses, making it challenging to assess the reliability and credibility of the information provided. Ensuring transparency and interpretability in research papers becomes more challenging with such models. ChatGPT should cite the sources for its data, like Google Bard does.
Plagiarism concerns: Because of its vast training data from the Internet, ChatGPT may inadvertently generate text that resembles or replicates existing content without proper citation or attribution. Researchers must be cautious about unintentional plagiarism and ensure that generated content is appropriately referenced and original. So, all ChatGPt-generated articles need to be double checked using antiplagiarism software.

In this commentary I have provided a comprehensive step-by-step guide for researchers and authors on harnessing the power of ChatGPT in the realm of research and publication. By exploring crucial aspects, such as data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations, the guide equips researchers with the necessary knowledge and tools to effectively integrate ChatGPT into their scientific workflows. 8

Through clear instructions, examples, and guidelines, researchers can navigate the complexities of using ChatGPT, leading to enhanced productivity and improved quality in their research output. Moreover, I address the challenges associated with biases, interpretability, and plagiarism concerns, ensuring the responsible and ethical usage of ChatGPT as a research tool.

The significance of this research lies in its ability to bridge the gap between the rapid advancements in language models like ChatGPT and the research and publication process. By empowering researchers with the skills to leverage ChatGPT effectively, this guide fosters innovation, drives scientific progress, and opens up new possibilities for transformative contributions to various fields. 9

As language-driven technologies continue to evolve, researchers must stay abreast of the latest advancements and best practices. The step-by-step guide presented in this commentary serves as a valuable resource, providing researchers with the knowledge and guidance necessary to maximize the potential of ChatGPT in their research endeavors. By embracing the capabilities of ChatGPT and ensuring its responsible and ethical use, researchers can revolutionize the way research and publications are conducted. With ChatGPT as a powerful tool in their arsenal, researchers are poised to make significant strides in their respective fields, pushing the boundaries of scientific knowledge and ushering in a new era of language-driven innovation. 10

However, and to reiterate, I cannot overemphasize that ChatGPT has, at present, many disadvantages, including inconsistencies, bias, and plagiarism concerns, that must be addressed by the human author before the article is submitted for publication to a journal, as well as prior to publication, because the human author(s) is solely responsible for their research integrity and accurate reporting.

In conclusion, I have attempted to provide researchers with a comprehensive understanding of how to effectively leverage ChatGPT for research and publication purposes. It has also highlighted the problems and precautions that the human author(s) must take before publishing ChatGPT-generated content. By embracing this step-by-step guide, researchers can unlock the full potential of ChatGPT, driving scientific progress and shaping the future of research and publications.

Please use ChatGPT only if allowed by your institution, research lab, and the journal in question.
Please acknowledge ChatGPT within your manuscript/published paper wherever you are using it.
Please do not fabricate or plagiarize data. ChatGPT can be used only for summarizing texts, improving English writeups, and brainstorming ideas, and not for creating fabricated research raw data.

Acknowledgment.

The author acknowledges that this article was partially generated by ChatGPT (powered by OpenAI’s language model, GPT-3; http://openai.com ). The editing was performed by the human author.

Disclosures. The author declare no conflicts or financial interest in any product or service mentioned in the manuscript, including grants, equipment, medications, employment, gifts, and honoraria.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

View all journals
Explore content
About the journal
Publish with us
Sign up for alerts
Published: 28 July 2023

Special feature

Application ChatGPT in conducting systematic reviews and meta-analyses

Simpy Amit Mahuli 1 ,
Arpita Rai 2 ,
Amit Vasant Mahuli 3 &
Ansul Kumar 4

British Dental Journal volume 235 , pages 90–92 ( 2023 ) Cite this article

5102 Accesses

11 Citations

Metrics details

You have full access to this article via your institution.

Systematic reviews and meta-analyses, which involve thorough literature searches and synthesis, are essential for evidence-based decision-making. With the growing number of publications, thorough review takes more time. A systematic review often takes more than 15 months to complete, and the long conception-completion interval may render a systematic review outdated by the time they are ready to be submitted and published. 1 , 2

Artificial intelligence (AI)-based quick approaches are being developed in response to the growing demand for screening and data extraction techniques that are more effective. These techniques automate decision-making by utilising machine learning (ML) algorithms and natural language processing (NLP) to extract pertinent information from textual material. These AI-based methods have the potential to accelerate the processes of systematic reviews and evidence synthesis while requiring less human labour. 3 , 4

ChatGPT is a Large Language Model (LLM) developed by OpenAI (OpenAI, L.L.C., San Francisco, CA, USA) which has tremendous potential to revolutionise the healthcare industry. ChatGPT has been effectively used for a variety of tasks in healthcare, including conducting literature reviews, analysing datasets, writing academic papers, documentation, and enhancing clinical workflow. ChatGPT is a significant advancement in the field of NLP. It generates human-like text by mimicking human language processing abilities using deep learning techniques and neural networks. Owing to its training on diverse datasets, it is able to provide pertinent responses to human prompts by processing large amounts of information. The easy accessibility and free availability have contributed to the success ChatGPT version 3.5 platform. 5

We tried to use ChatGPT for conducting Risk of Bias analysis and data extraction from a randomised controlled trial. The response of ChatGPT was surprising, to say the least. Conducting such processes through ChatGPT is simple and straightforward.

Firstly, to conduct a ROB analysis effectively using AI, obtaining the full-text version of the article under evaluation is crucial. This ensures that all relevant information and details necessary for the assessment are available. As an AI tool, it does not have real-time browsing capabilities, so it cannot search the internet or access the latest research articles. Additionally, it being a text-based AI, we cannot upload or import text/pdf files into the chatbox. However, ChatGPT can still try to assist us with general questions or provide guidance based on the information we provide from the study. If we have any specific questions or excerpts from the study that we would like ChatGPT to analyse or discuss, we can paste them into the chat box, and ChatGPT will do its best to assist.

AI provides validation to the information obtained through human effort and may even catch some details that are missed by the human eye.

Secondly, we need to provide clear and specific instructions to the tool for it to provide an appropriate response. Hence when prompted 'Can you use the ROBINS-I tool to evaluate "(Materials and methods from the full-text article)"', it generated a detailed response highlighting the various lacunae in the methodology in context of the Biases included in the ROBINS-I tool ( Fig. 1 and Fig. 2 ). This assessment does not eliminate the need for a human expert; however, it considerably reduces the time and effort required for the process. Also, AI provides validation to the information obtained through human effort and may even catch some details that are missed by the human eye. Additionally, ChatGPT is extremely helpful in the interpretation of studies for those who are not so fluent in the language. While ChatGPT can comprehend and generate text in languages other than English to some extent, its proficiency may vary across different languages. It's worth noting that ChatGPT's performance is generally more robust in English, as the majority of its training data is in English.

Screenshot of query for RoB analyis

Screenshot of ChatGPT's response to RoB analysis

Next, we tried to use ChatGPT for data extraction. By sharing the complete text and specifying the desired information or data to be extracted, AI can be of assistance. Hence, following various prompts from us, ChatGPT extracted data like mean values, standard deviation and sample size for study groups and sub-groups and presented it. Also, it was able to extract information from the tables provided, though it is not possible to paste a table in the chatbox. We can paste the data in the table en masse into the chatbox and it was able to interpret and extract information from it ( Fig. 3 and Fig. 4 ). Needless to say, this will reduce the time required for data extraction as well as ensure accuracy of the values, thereby reducing human errors.

Screenshot of query for data extraction from text

Response from ChatGPT for various queries for data extraction

AI methods are increasingly integrated into healthcare reviews to streamline processes. A recent systematic review by Blaizot et al. identified and examined automated tools and platforms that utilise artificial intelligence (AI) techniques. It assessed the pros and cons associated with the use of these methods in conducting systematic reviews. They identified various tools like Rayyan, Robot Reviewer, EPPI-reviewer, SWIFT-review, and Abstrackr which were employed for different review stages. Most included reviews acknowledged that screening with AI methods generally demonstrates low risks and enhances efficiency. However, possibility of missing relevant articles and issues in data extraction required human intervention. 4

ChatGPT possesses several distinct advantages in comparison to other AI tools. Its ability to retain context and coherence during conversations equips it to comprehend and respond to complex queries. It is extremely versatile which is demonstrated through its proficiency in handling various tasks, including factual inquiries, explanatory responses, creative content generation, and problem-solving assistance. ChatGPT is continuously evolving through regular updates and fine-tuning based on user feedback and new training data, enhancing its performance and accuracy over time. 5

It is crucial to acknowledge that ChatGPT also has limitations. These include the potential for generating incorrect or biased responses and its reliance on pre-existing data. Users should exercise critical thinking and independently verify information obtained from any AI tool. Currently, it is unable to process visual information; however, this issue has been addressed in ChatGPT 4.0. Additionally, the model's output heavily relies on user input; minor changes in the query can lead to significant alterations in the response. 5

This was the first attempt to test the feasibility of using ChatGPT in the tedious task of conducting systematic reviews and meta-analyses. It shows promise in reducing workload and time, but careful implementation and validation are necessary. We as researchers need to interact more with this tool to completely understand its applicability in generating evidence.

Borah R, Brown A W, Capers P L, Kaiser K A. Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the PROSPERO registry. BMJ Open 2017; doi: 10.1136/bmjopen-2016-012545.

Yaffe J, Montgomery P, Hopewell S, Shepard L D. Empty reviews: a description and consideration of Cochrane systematic reviews with no included studies. PLoS One 2012; doi: doi: 10.1371/journal.pone.0036626.

Chollet F. Deep learning with Python. pp 361. Shelter Island, New York: Manning Publications Co, 2018.

Blaizot A, Veettil S K, Saidoung P, Moreno-Garcia C F et al . Using artificial intelligence methods for systematic review in health sciences: A systematic review. Res Synth Methods 2022; 13: 353-362.

OpenAI. Introducing ChatGPT. Available at: https://openai.com/blog/chatgpt (accessed 19 May 2023).

Download references

Author information

Authors and affiliations.

PhD Scholar, Rajendra Institute of Medical Sciences (RIMS), Bariatu, Ranchi – 834009, India

Simpy Amit Mahuli

Associate Professor, Oral Medicine and Radiology, Rajendra Institute of Medical Sciences (RIMS), Bariatu, Ranchi – 834009, India

Associate Professor, Public Health Dentistry, Rajendra Institute of Medical Sciences (RIMS), Bariatu, Ranchi – 834009, India

Amit Vasant Mahuli

Associate Professor, Cardiothoracic and Vascular Surgery, Dental College, Rajendra Institute of Medical Sciences, Bariatu, India

Ansul Kumar

You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Simpy Amit Mahuli , Arpita Rai , Amit Vasant Mahuli or Ansul Kumar .

Rights and permissions

Reprints and permissions

About this article

Cite this article.

Mahuli, S., Rai, A., Mahuli, A. et al. Application ChatGPT in conducting systematic reviews and meta-analyses. Br Dent J 235 , 90–92 (2023). https://doi.org/10.1038/s41415-023-6132-y

Download citation

Published : 28 July 2023

Issue Date : 28 July 2023

DOI : https://doi.org/10.1038/s41415-023-6132-y

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

This article is cited by

Ai-assisted boolean search.

J. M. Cherian
K. G. Varghese

British Dental Journal (2023)

AI-based article screening

M. Mehrabanian

Quick links

Explore articles by subject
Guide to authors
Editorial policies

Literature Reviews

Getting Started
Choosing a Type of Review
Developing a Research Question
Searching the Literature
Searching Tips
ChatGPT [beta]
ChatGPT Resources
Documenting your Search
Using Citation Managers
Concept Mapping
Writing the Review
Further Resources

UM's Report on GenerativeAI

The initial report from the U-M Generative Artificial Intelligence Advisory (GAIA) Committee.

—User-friendly Interface that allows faculty, staff and students to engage in chat-based queries and benefit from the expertise of GENAI technology

— U-M GPT, enhances, teaching learning research in collaboration, providing a valuable and equitable resource for the entire university community

— designed to be accessible, including for use with screen readers

— provides access to GPT-3.5 and GPT-4 with no charge

https://chat.openai.com

The knowledge cutoff for the ChatGPT 3.5 is September 2021 and it has no access to the Internet. Academic users may consider alternatives such as Semantic Scholar, Elicit, Consensus or other AI-powered tools for doing real-time literature reviews.
Input/ Output length - ChatGPT-3.5 allows a maximum token limit of 4096 tokens. According to ChatGPT " On average, a token in English is roughly equivalent to 4 bytes or characters. English words are typically around 5 characters long. This means that, very roughly, you could fit around 800 to 1000 English words within 4096 tokens."
Notes : (1) According to ChatGPT, the generated responses are non-deterministic by default. So if you run the searches again and get slightly or very different results than the ones listed on this guide, it's likely due to this factor. (2) While ChatGPT or Bing Chat searches offer conversational interaction, they might not be a substitute for the rigor and reliability of traditional academic database searches.

KEYWORD GENERATION

Write a literature review abstract based on the following keywords: Keywords: Artificial Intelligence, Employment Trends, Skill Development, Future Workforce

Infant death Neonatal mortality (referring specifically to deaths within the first 28 days of life) Perinatal mortality (referring to deaths occurring during the period from 22 completed weeks of gestation to 7 completed days after birth) Early childhood mortality (referring to deaths occurring within the first five years of life) Child mortality (referring to deaths occurring before the age of 18) [Press the Regenerate button to get more.]

Example - RELATED WORDS What are the related words of infant mortality?

Neonatal mortality, Post-neonatal mortality, Stillbirths, Low birth weight, Malnutrition, Infectious diseases, Vaccination, Maternal health, Access to healthcare, Poverty, Social inequality, Sanitation, Hygiene, Water quality, Childbirth complications, Congenital abnormalities, Birth defects, Maternal age, Under-five mortality, Child mortality, Perinatal mortality, Preterm birth, Low birth weight, Sudden infant death syndrome (SIDS), Maternal mortality, Postnatal care, Malnutrition, Immunization, Access to healthcare, Clean water and sanitation, Congenital anomalies, Infant health disparities, Infant mortality rate (IMR), Infant survival.

(("Infant Death"[Mesh] OR "Sudden Infant Death Syndrome"[Mesh] OR "Infant Mortality"[Mesh] OR "Perinatal Mortality"[Mesh] OR "Neonatal Mortality"[Mesh] OR "Fetal Mortality"[Mesh] OR "Infant Death" OR "Sudden Infant Death Syndrome" OR "Infant Mortality" OR "Perinatal Mortality" OR "Neonatal Mortality" OR "Fetal Mortality") AND ("Risk Factors"[Mesh] OR "Etiology"[Mesh] OR "Prevention and Control"[Mesh] OR "Interventions"[Mesh] OR "Public Health"[Mesh] OR "Health Disparities"[Mesh] OR "Healthcare Disparities"[Mesh] OR "Poverty"[Mesh] OR "Malnutrition"[Mesh] OR "Infection"[Mesh] OR "Congenital Abnormalities"[Mesh] OR "Prematurity"[Mesh] OR "Low Birth Weight"[Mesh] OR "Maternal Education"[Mesh] OR "Maternal Health"[Mesh] OR "Risk Factors" OR "Etiology" OR "Prevention and Control" OR "Interventions" OR "Public Health" OR "Health Disparities" OR "Healthcare Disparities" OR "Poverty" OR "Malnutrition" OR "Infection" OR "Congenital Abnormalities" OR "Prematurity" OR "Low Birth Weight" OR "Maternal Education" OR "Maternal Health"))

Comments and Suggestions: #1 -This search string may not work on all database platforms. For example, Medline (OVID) may not be able to run it, Medline & CINAHL (EBSCO) can run it without any problems while PubMed will run it but it will indicate which MeSH terms are not indexed. See PubMed's search History and Details under Advanced . #2 -This is just one possible search string and you may need to adjust it based on your specific research questions and the databases you are using. #3 - It might be easier if you break the task into 3 parts: ask the chatbot give you the synonyms > ask it to give you the thesauri terms > and ask it to combine them.

RESEARCH QUESTION

Increased risk of sudden infant death syndrome (SIDS) Increased risk of premature birth Increased risk of low birth weight Increased risk of respiratory problems in newborns Increased risk of respiratory problems in infants exposed to secondhand smoke Increased risk of developing asthma and other respiratory illnesses later in life for infants exposed to secondhand smoke Please generate a literature review that addresses the research question: 'What are the effects of social media on the mental health of adolescents? [Author's note : If you ask for the specific studies, ChatGPT may generate non-existent references or false knowledge. To find out why Large Language Models hallucinate, check out this WiKi article: Hallucination (artificial intelligence) and this blog post - A Gentle Introduction to Hallucinations in Large Language Models by Adrian Tam ]

DATABASE RECOMMENDATIONS

Heath Science - Which databases to use to find articles on the EFFECTS OF MATERNAL SMOKING ON INFANT DEATH? PubMed: This is a database of biomedical literature from the National Library of Medicine. It includes articles from medical journals and other sources on a wide range of health-related topics. Embase: This is a database of biomedical literature that covers more international and pharmaceutical content than PubMed. It includes articles from medical journals and other sources on a wide range of health-related topics. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions, including interventions related to maternal smoking and infant death. Scopus: This is a multidisciplinary database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. Web of Science: This is a database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. CINAHL: This is a database of nursing and allied health literature, including articles on maternal smoking and infant death. [Note: The response above was copied and pasted directly from ChatGPT. No editing was added.] Education -- I am doing a meta-analysis on k-12 STEM education. What databases should I use? ERIC : This is a database of education research and information, including articles from journals, reports, and conference papers. It is a commonly used database for educational research. Education Source : This is a comprehensive database of education research and information, including articles from journals, books, and conference papers. Web of Science: This is a multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. Scopus: This is another multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. PsycINFO: This is a database of psychology research, including articles from journals, books, and dissertations. It can be useful for research on STEM education that includes psychological factors. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions including interventions related to education.

Example: ACT-AS-AN-EXPERT PROMPT Here's an alternative way to consolidate all the questions into a single consultation by using this popular Act-As-An-Expert prompt, aka, system message prompt: I am going to conduct a systematic review on games and mathematics related to K-12 education I want you to act as a systematic review expert. I will ask you some questions related to my research topic and you advise me on how to do it.

GREY LITERATURE

Please show me all the resources that offer grey literature for conducting research in the field of education ERIC (Education Resources Information Center): https://eric.ed.gov/ OpenGrey: http://www.opengrey.eu/ British Education Index: https://www.ebscohost.com/academic/british-education-index WorldCat: https://www.worldcat.org/ ProQuest Dissertations & Theses Global: https://www.proquest.com/products-services/pqdtglobal.html EThOS (Electronic Theses Online Service): https://ethos.bl.uk/ Institutional Repositories of universities and academic institutions (search for specific institution repositories) American Educational Research Association (AERA): https://www.aera.net/ National Education Association (NEA): https://www.nea.org/ Association for Supervision and Curriculum Development (ASCD): http://www.ascd.org/ RAND Corporation: https://www.rand.org/ National Center for Education Research (NCER): https://ies.ed.gov/ncer/ National Center for Education Statistics (NCES): https://nces.ed.gov/ European Educational Research Association (EERA): https://www.eera-ecer.de/ UNESCO International Institute for Educational Planning (IIEP): http://www.iiep.unesco.org/ Organization for Economic Cooperation and Development (OECD): https://www.oecd.org/education/ Education Development Center (EDC): https://www.edc.org/ National Institute for Educational Policy Research (NIER) - Japan: https://www.nier.go.jp/ Australian Council for Educational Research (ACER): https://www.acer.org/ Canadian Education Association (CEA): https://www.cea-ace.ca/ My topic is about stem education. Which grey literature databases should I use? STEM Education Research Centre (SERC) Grey Literature Database National STEM Education Research Repository (NSERR) National Science Digital Library (NSDL) STEM Education Resource Center (SERC) GrayLit Network STEM Education Grey Literature Library

MORE RESOURCES

<< Previous: AI Lit Searching [beta]
Next: Organizing the Literature >>
Last Updated: May 9, 2024 11:44 AM
URL: https://guides.lib.umich.edu/litreview

FIU Libraries
RefTech LibGuides
Artificial Intelligence Now: ChatGPT + AI Literacy Toolbox
Literature Reviews with Prompts

Artificial Intelligence Now: ChatGPT + AI Literacy Toolbox: Literature Reviews with Prompts

Literacy Tutorials
AI LibGuides
AI Literacy
AI + Art News
AI Plagiarism + Citation
Which AI tools should I choose?
Faculty + Academic Writing
ChatGPT on InfoLit
Libraries + AI
Art + Image Prompts
Prompt Literacy
Text Prompts
Scholarship + Publishing
Students + AI Use
FIU Library Resources
How does ChatGPT work?
Zoom Recordings: AI Workshops
ALA 2024: Breaking Boundaries

Resources on Lit Reviews & AI

How to Use ChatGPT to Accelerate Literature Review I’d like to show you how I use ChatGPT to speed up my literature review process. The topic I am exploring is heterogeneity(diversity) learning. I started with the keyword “Info-GAIL” as I read about it when using GAIL in the past.
ChatGPT Simple Literature Review Template The evolution of library services in the digital age has seen a significant shift towards automation and artificial intelligence applications, with OpenAI's ChatGPT being one of the most popular tools. This literature review explores the trends in the application of ChatGPT in library settings, focusing on user engagement and support services from 2015 to 2023.
ChatGPT as a Tool for Library Research – Some Notes and Suggestions I see ChatGPT and its alternatives as having partial value as tools for library searching. You can use them without any training, but they will perform better when you know some details about them.

9 Ways To Use ChatGPT To Write A Literature Review (WITHOUT Plagiarism) Video

Step-by-Step

How to Use ChatGPT to Write a Literature Review With Prompts

Writing a literature review can be a challenging task for researchers and students alike. It requires a comprehensive understanding of the existing body of research on a particular topic. However, with the advent of advanced language models like ChatGPT, the process has become more accessible and efficient.

Discover how to effectively utilize ChatGPT as a research assistant to write a comprehensive and SEO-friendly literature review. Follow our step-by-step guide to leverage this powerful tool, optimize your review for search engines, and contribute to the scholarly conversation in your field.

A Step-by-Step Guide: How to Use ChatGPT for Writing a Literature Review

Step 1: Defining Your Research Objective Before diving into the literature review process, it is crucial to define your research objective.

Clearly articulate the topic, research question, or hypothesis you aim to address through your literature review. This step will help you maintain focus and guide your search for relevant sources.

Step 2: Identifying Keywords and Search Terms To effectively use ChatGPT to assist in your literature review, you need to identify relevant keywords and search terms related to your research topic.

These keywords will help you narrow down your search and gather pertinent information. Consider using tools like Google Keyword Planner or other keyword research tools to discover commonly used terms in your field.

Step 3: Familiarizing Yourself with ChatGPT Before engaging with ChatGPT, it is essential to understand its capabilities and limitations. Familiarize yourself with the prompts and commands that work best with the model.

Keep in mind that ChatGPT is an AI language model trained on a vast amount of data, so it can provide valuable insights and suggestions, but it’s important to critically evaluate and validate the information it generates.

Step 4: Generating an Initial Literature Review Outline Start by creating an outline for your literature review. Outline the main sections, such as the introduction, methodology, results, discussion, and conclusion.

Within each section, jot down the key points or subtopics you want to cover. This will help you organize your thoughts and structure your review effectively.

Step 5: Engaging with ChatGPT for Research Assistance Once you have your outline ready, engage with ChatGPT for research assistance.

Begin by providing a clear and concise prompt that specifies the topic, context, and any specific questions you have. For example, “What are the current trends in [your research topic]?” or “Can you provide an overview of the main theories on [your research question]?”

Step 6: Reviewing and Selecting Generated Content ChatGPT will generate a response based on your prompt. Carefully review the content generated, considering its relevance, accuracy, and coherence.

Extract key points, relevant references, and insightful arguments from the response and incorporate them into your literature review. Be sure to cite and attribute the sources appropriately.

Step 7: Ensuring Coherence and Flow While ChatGPT can provide valuable content, it’s important to ensure the coherence and flow of your literature review.

Use your critical thinking skills to connect the generated content with your research objective and existing knowledge. Rearrange, rephrase, and expand upon the generated text to ensure it aligns with the structure and purpose of your review.

Step 8: Editing and Proofreading Once you have incorporated the generated content into your literature review, thoroughly edit and proofread the document.

Check for grammatical errors, consistency in referencing, and overall clarity. This step is crucial to ensure your literature review is polished and professional.

ChatGPT prompts to Write a Literature Review

Prompts you can use when engaging with ChatGPT for research assistance in writing a literature review:

“Can you provide an overview of the main theories and concepts related to [your research topic]?”

“What are the current trends and developments in [your research field]?”

“Can you suggest some key studies or research papers on [specific aspect of your research topic]?”

“What are the main methodologies used in conducting research on [your research topic]?”

“Can you provide a critical analysis of the existing literature on [your research question]?”

“Are there any gaps or areas of controversy in the literature on [your research topic] that need further exploration?”

“What are the key findings and conclusions from the most recent studies on [your research topic]?”

“Can you suggest some reputable journals or publications explore for relevant literature in [your research field]?”

“What are the different perspectives or schools of thought in the literature on [your research topic]?”

“Can you provide a summary of the historical background and evolution of research on [your research topic]?”

Remember to provide clear and specific instructions in your prompts to guide ChatGPT in generating relevant and accurate content for your literature review.

Using ChatGPT to write a literature review can greatly facilitate the research process. By following a step-by-step approach, researchers can effectively leverage ChatGPT’s capabilities to gather insights, generate content, and enhance the quality of their literature review. However, it is important to approach the generated content critically, validate it with reliable sources, and ensure coherence within the review.

<< Previous: Art + Image Prompts
Next: Prompt Literacy >>
Last Updated: May 23, 2024 12:24 PM
URL: https://library.fiu.edu/ai

Joyner Library
Laupus Health Sciences Library
Music Library
Digital Collections
Special Collections
North Carolina Collection
Teaching Resources
The ScholarShip Institutional Repository
Country Doctor Museum

Literature Review: Using ChatGPT

About Literature Reviews
How to Conduct your Lit Review
A Few Writing Tips
A Few Helpful Resources
A Silly Example
Using ChatGPT

What is AI, ChatGPT, and large-language modeling?

Artificial intelligence (AI) , in the context of this guide, is the use of datasets to train computer models to emulate human thought processes (IBM, n.d.). It is the emulation itself that may convince information consumers of the supposed "intelligence" of a machine; the more convincing the emulation, the more users are prone to trust the generated information.

ChatGPT is a generative large language model which has gained popularity since late 2021. The name stands for Chat Generative Pre-trained Transformer. GPT models are programmed to mimic the look and feel of engaging in a realistic conversation with another human being; however, bias and inaccuracy remain a considerable risk ( Kocoń, J., 2023).

Large language models (LLMs) are AI models that utilize networked datasets, emulating the neural pathways of the human brain, which assists in the appearance of actual cognition (Birhane et al., 2023).

Birhane, A., Kasirzadeh, A., Leslie, D., & Wachter, S. (2023). Science in the age of large language models. Nature Reviews Physics . https://www.nature.com/articles/s42254-023-00581-4

IBM. (n.d.). What is artificial intelligence (AI)? https://www.ibm.com/topics/artificial-intelligence Retrieved 27 April 2023.

Read more here: Generative AI in the Classroom & Research

What can I use ChatGPT for?

First and most importantly: check with your instructor that using generative AI is allowed for your class! This information should be added in your course syllabus with language indicating whether and to what extent AI can be used on assignments. If you are not sure, ask your instructor first .

From my biased perspective (that of a librarian), here is a brief list of ways you could use ChatGPT (if allowed for your class). This list is not exhaustive of all ideas.

Keyword generation. Having trouble thinking of other ways to describe a concept? Ask ChatGPT to help!
Narrowing/broadening your topic. Not getting any results? Getting way too many results? Use ChatGPT to help you brainstorm ways you can adjust your research question so that you can find the most effective sources.
Setting the right tone. Want to create a patient education document in plain language but not quite sure how to translate the nursing jargon into easy-to-understand statements? ChatGPT can help you think of ways to ensure your tone matches your preferred audience.

What shouldn't I use ChatGPT for?

Because of bias and limitations from human contributions, it is imperative to approach generative AI with caution.

If your instructor has approved the use of ChatGPT or other generative AI in the class, below is a brief list of ways you should NOT use it. Again, this list is not exhaustive.

Writing your assignments. This may be considered a form of plagiarism as the generated language is not your own original writing. If you use ChatGPT in this way without credit, you may be found in violation of the University's Academic Integrity policies. If you aren't sure, check with your instructor.
Searching for sources. Do not use ChatGPT in lieu of conducting a literature search through the library resources. ChatGPT has a bad habit of "hallucinating" results; in other words, it will generate answers that sound right but that are not actual sources that exist. ChatGPT is not a search engine or a database.
Creating accurate citations. ChatGPT is about as good as any other citation generator out there, which is to say that it is hit or miss. ChatGPT may leave off required elements of a citation, invent elements (for instance, generating incorrect DOIs or URLs), and fail to follow citation style formatting requirements. If you use ChatGPT for citation generation, be sure to double- and triple-check every citation thoroughly before submitting your assignment.

Ask a Librarian

Chat with a librarian is available 9-5 Monday-Saturday.

You can also contact a librarian .

1-888-820-0522 (toll free)

252-744-2230

Or email us:

[email protected]

Provide Feedback on this Guide

Please follow the link below to complete a short survey and provide feedback on this guide.

Research Guide Satisfaction Survey

Should I cite ChatGPT?

Citing ChatGPT and other generative AI will allow your work to remain transparent while also demonstrating ethical considerations. If generative AI is used in research, best practice would dictate to mention the use of this tool in the narrative.

Suggestions for citations may be found below:

American Psychological Association (APA)
Chicago Manual of Style
Modern Language Association (MLA)
<< Previous: A Silly Example
Last Updated: Jan 12, 2024 1:21 PM
URL: https://libguides.ecu.edu/lit_reviews

Interesting
Scholarships
UGC-CARE Journals

Step-by-Step Guide: How to Use ChatGPT to Write a Literature Review With Prompts

Step-by-Step Guide: How to Use ChatGPT for Writing a Literature Review

In this step-by-step guide, ilovephd will explore how you can leverage ChatGPT to write a compelling literature review that is both informative.