chatgpt writing literature review

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.

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

• 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

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.

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

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.

• Academic Writing
• AI writing tool
• literature review guide
• literature review tips
• research assistance
• research process
• research writing
• write literature review

10 Trending AI Tools for Dynamic Graph Visualization

List of phd and postdoc fellowships in india 2024, 10 mind-blowing ai projects transforming medical imaging, most popular, abstract template for research paper, 10 types of plagiarism – every academic writer should know – updated, the harsh reality: why revoked graduate degrees aren’t easily reclaimed, top 50 research institutions in india: nirf rankings 2024, top 35 scopus indexed journals in english literature, how to create graphical abstract, list of research topics in environmental engineering, indo-russian joint research call for proposals 2024, newly accepted scopus indexed journals june 2024, top 10 scopus indexed agronomy and crop science journals, best for you, 24 best online plagiarism checker free – 2024, what is phd, popular posts, popular category.

• POSTDOC 317
• Interesting 257
• Journals 235
• Fellowship 133
• Research Methodology 102
• All Scopus Indexed Journals 93

Mail Subscription

iLovePhD is a research education website to know updated research-related information. It helps researchers to find top journals for publishing research articles and get an easy manual for research tools. The main aim of this website is to help Ph.D. scholars who are working in various domains to get more valuable ideas to carry out their research. Learn the current groundbreaking research activities around the world, love the process of getting a Ph.D.

Contact us: [email protected]

Google News

Copyright © 2024 iLovePhD. All rights reserved

• Artificial intelligence

• FIU Libraries
• 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

Dr. Somasundaram R | https://www.ilovephd.com/ | Copyright © 2019-2023 – iLovePhD | May 19, 2023

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: Jul 30, 2024 4:27 PM
• URL: https://library.fiu.edu/ai

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: 12 August 2024

An empirical investigation of the impact of ChatGPT on creativity

• Byung Cheol Lee   ORCID: orcid.org/0000-0001-5353-8056 1   na1 &
• Jaeyeon (Jae) Chung   ORCID: orcid.org/0000-0003-0770-2884 2   na1  

Nature Human Behaviour ( 2024 ) Cite this article

1296 Accesses

59 Altmetric

Metrics details

• Business and management
• Human behaviour

This paper investigates the potential of ChatGPT for helping humans tackle problems that require creativity. Across five experiments, we asked participants to use ChatGPT (GPT-3.5) to generate creative ideas for various everyday and innovation-related problems, including choosing a creative gift for a teenager, making a toy, repurposing unused items and designing an innovative dining table. We found that using ChatGPT increased the creativity of the generated ideas compared with not using any technology or using a conventional Web search (Google). This effect remained robust regardless of whether the problem required consideration of many (versus few) constraints and whether it was viewed as requiring empathetic concern. Furthermore, ChatGPT was most effective at generating incrementally (versus radically) new ideas. Process evidence suggests that the positive influence of ChatGPT can be attributed to its capability to combine remotely related concepts into a cohesive form, leading to a more articulate presentation of ideas.

This is a preview of subscription content, access via your institution

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 12 digital issues and online access to articles

111,21 € per year

only 9,27 € per issue

Buy this article

• Purchase on Springer Link
• Instant access to full article PDF

Prices may be subject to local taxes which are calculated during checkout

Similar content being viewed by others

Best humans still outperform artificial intelligence in a creative divergent thinking task

Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT

The consequences of generative AI for online knowledge communities

Data availability.

All data, including the secondary dataset and the experiments, can be found in the Open Science Framework at https://osf.io/rzn87/ .

Code availability

The corresponding code can be found in the Open Science Framework at https://osf.io/rzn87/ .

Hu, K. ChatGPT sets record for fastest-growing user base—analyst note. Reuters (3 February 2023); https://www.reuters.com/technology/chatgpt-sets-record-fastest-growing-user-base-analyst-note-2023-02-01/

Tong, A. Exclusive: ChatGPT traffic slips again for third month in a row. Reuters (7 September 2023); https://www.reuters.com/technology/chatgpt-traffic-slips-again-third-month-row-2023-09-07/

GPT-4 Technical Report (OpenAI, 2023); https://cdn.openai.com/papers/gpt-4.pdf

Kung, T. H. et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLoS Digit. Health 2 , e0000198 (2023).

Article   PubMed   PubMed Central   Google Scholar  

Stevenson, C., Smal, I., Baas, M., Grasman, R. & van der Maas, H. Putting GPT-3’s creativity to the (alternative uses) test. In Proc. 13th International Conference on Computational Creativity (eds Hedblom, M. M. et al.) 164–168 (Association for Computational Creativity, 2022).

Góes, F., Volpe, M., Sawicki, P., Grzes, M. & Watson, J. Pushing GPT’s creativity to its limits: alternative uses and Torrance Tests. In Proc. 14th International Conference on Computational Creativity (eds Pease, A. et al.) 342–346 (Association for Computational Creativity, 2023).

Summers-Stay, D., Voss, C. R. & Lukin, S. M. Brainstorm, then select: a generative language model improves its creativity score [Paper Presentation]. In A AAI-23 Workshop on Creative AI Across Modalities (2023).

Bubeck, S. et al. Sparks of artificial general intelligence: early experiments with GPT-4. Preprint at arXiv https://doi.org/10.48550/arXiv.2303.12712 (2023).

Kaufman, J. C., Beghetto, R. A. & Watson, C. Creative metacognition and self-ratings of creative performance: a 4-C perspective. Learn. Individ. Differ. 51 , 394–399 (2016).

Article   Google Scholar  

Plucker, J. A. & Renzulli, J. S. in Handbook of Creativity (eds Sternberg, R. J. & Renzulli, J. S.) 35–61 (Cambridge Univ. Press, 1999).

Sternberg, R. J. & Lubart, T. I. in Handbook of Creativity (eds Sternberg, R. J. & Renzulli, J. S.) 3–15 (Cambridge Univ. Press, 1999).

Burroughs, J., Moreau, C. P. & Mick, D. in Handbook of Consumer Psychology (eds Haugtvedt, C. et al.) 1011–1038 (Routledge, 2008).

Moreau, C. P. & Dahl, D. W. Designing the solution: the impact of constraints on consumers’ creativity. J. Consum. Res. 32 , 13–22 (2005).

Runco, M. A., Illies, J. J. & Eisenman, R. Creativity, originality, and appropriateness: what do explicit instructions tell us about their relationships? J. Creat. Behav. 39 , 137–148 (2005).

Mednick, S. A. The associative basis of the creative process. Psychol. Rev. 69 , 220–232 (1962).

Article   PubMed   CAS   Google Scholar  

Beaty, R. E., Silvia, P. J., Nusbaum, E. C., Jauk, E. & Benedek, M. The roles of associative and executive processes in creative cognition. Mem. Cogn. 42 , 1186–1197 (2014).

Koestler, A. The Act of Creation (Hutchinson & Co., 1964).

Levin, I. Creativity and two modes of associative fluency: chains and stars. J. Pers. 46 , 426–437 (1978).

Benedek, M., Könen, T. & Neubauer, A. C. Associative abilities underlying creativity. Psychol. Aesthet. Creat. Arts 6 , 273–281 (2012).

Shneiderman, B. Creativity support tools. Commun. ACM 45 , 116–120 (2002).

Herring, S. R., Jones, B. R. & Bailey, B. P. Idea generation techniques among creative professionals. In Proc. 2009 42 nd Hawaii International Conference on System Sciences (ed. Sprague, R. H.) 1–10 (IEEE, 2009).

Guzik, E. E., Byrge, C. & Gilde, C. The originality of machines: AI takes the Torrance Test. J. Creat. 33 , 100065 (2023).

Hubert, K. F., Awa, K. N. & Zabelina, D. L. The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks. Sci. Rep. 14 , 3440 (2024).

Article   PubMed   PubMed Central   CAS   Google Scholar  

Haase, J. & Hanel, P. H. P. Artificial muses: generative artificial intelligence chatbots have risen to human-level creativity. J. Creat. 33 , 100066 (2023).

Mehta, R., Zhu, R. & Cheema, A. Is noise always bad? Exploring the effects of ambient noise on creative cognition. J. Consum. Res. 39 , 784–799 (2012).

Grosskopf, S. in The Measurement of Productive Efficiency: Techniques and Applications (eds Fried, H. O. et al.) 160–194 (Oxford University Press, 1993).

Coelli, T. J., Rao, D. S. P., O’Donnell, C. J. & Battese, G. E. An Introduction to Efficiency and Productivity Analysis (Springer Science & Business Media, 2005).

Jackson, F. Could ChatGPT REALLY slay Google? MailOnline looks at whether the trendy bot can put an end to internet giant’s £120 billion dominance by revamping how we search the net. Daily Mail (11 May 2023); https://www.dailymail.co.uk/sciencetech/article-11723499/Could-ChatGPT-replace-Google-Experts-weigh-win-race-AI-search-engine.html

Heaven, W. D. Chatbots could one day replace search engines. Here’s why that’s a terrible idea. MIT Technology Review (29 March 2022); https://www.technologyreview.com/2022/03/29/1048439/chatbots-replace-search-engine-terrible-idea/

Lucas, B. J. & Nordgren, L. F. The creative cliff illusion. Proc. Natl Acad. Sci. USA 117 , 19830–19836 (2020).

Dewar, R. D. & Dutton, J. E. The adoption of radical and incremental innovations: an empirical analysis. Manage. Sci. 32 , 1422–1433 (1986).

Madjar, N., Greenberg, E. & Chen, Z. Factors for radical creativity, incremental creativity, and routine, noncreative performance. J. Appl. Psychol. 96 , 730–743 (2011).

Article   PubMed   Google Scholar  

Johnson, A. Here’s what to know about OpenAI’s ChatGPT—what it’s disrupting and how to use it. Forbes (12 December 2022); https://www.forbes.com/sites/ariannajohnson/2022/12/07/heres-what-to-know-about-openais-chatgpt-what-its-disrupting-and-how-to-use-it/

Roose, K. How does ChatGPT really work? New York Times (28 March 2023); https://www.nytimes.com/2023/03/28/technology/ai-chatbots-chatgpt-bing-bard-llm.html

Lam, T. C. M., Kolomitro, K. & Alamparambil, F. C. Empathy training: methods, evaluation practices, and validity. J. Multidiscip. Eval. 7 , 162–200 (2011).

Kahriman, I. et al. The effect of empathy training on the empathic skills of nurses. Iran. Red Crescent Med. J. 18 , e24847 (2016).

Goldstein, A. P. & Michaels, G. Y. Empathy: Development, Training, and Consequences (Routledge, 2021).

Castelo, N., Bos, M. W. & Lehmann, D. R. Task-dependent algorithm aversion. J. Mark. Res. 56 , 809–825 (2019).

Longoni, C. & Cian, L. Artificial intelligence in utilitarian vs. hedonic contexts: the “word-of-machine” effect. J. Mark. 86 , 91–108 (2022).

Rosseel, Y. lavaan: an R package for structural equation modeling. J. Stat. Softw. 48 , 1–36 (2012).

Download references

Acknowledgements

The authors received no specific funding for this work.

Author information

These authors contributed equally: Byung Cheol Lee, Jaeyeon (Jae) Chung.

Authors and Affiliations

Department of Marketing, Bauer College of Business, University of Houston, Houston, TX, USA

Byung Cheol Lee

Department of Marketing, Jones Graduate School of Business, Rice University, Houston, TX, USA

Jaeyeon (Jae) Chung

You can also search for this author in PubMed   Google Scholar

Contributions

B.C.L. and J.C. engaged in idea generation, designed and performed research, analysed data and wrote the paper together.

Corresponding author

Correspondence to Byung Cheol Lee .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Peer review

Peer review information.

Nature Human Behaviour thanks Fabricio Góes, Max Kreminski and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

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

Supplementary information

Supplementary information.

Supplementary Notes A–K, Fig. 1, Tables 1–3 and references.

Reporting Summary

Rights and permissions.

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article.

Lee, B.C., Chung, J.(. An empirical investigation of the impact of ChatGPT on creativity. Nat Hum Behav (2024). https://doi.org/10.1038/s41562-024-01953-1

Download citation

Received : 11 September 2023

Accepted : 10 July 2024

Published : 12 August 2024

DOI : https://doi.org/10.1038/s41562-024-01953-1

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

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

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

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
• My Bibliography
• Collections
• Citation manager

Save citation to file

Email citation, add to collections.

• Create a new collection
• Add to an existing collection

Add to My Bibliography

Your saved search, create a file for external citation management software, your rss feed.

• Search in PubMed
• Search in NLM Catalog
• Add to Search

Using ChatGPT to conduct a literature review

Affiliation.

• 1 Department of Humanities, Czech University of Life Sciences Prague; Prague, Czech Republic.
• PMID: 36879536
• DOI: 10.1080/08989621.2023.2185514

PubMed Disclaimer

Similar articles

• Universal skepticism of ChatGPT: a review of early literature on chat generative pre-trained transformer. Watters C, Lemanski MK. Watters C, et al. Front Big Data. 2023 Aug 23;6:1224976. doi: 10.3389/fdata.2023.1224976. eCollection 2023. Front Big Data. 2023. PMID: 37680954 Free PMC article. Review.
• Revolutionizing Healthcare with ChatGPT: An Early Exploration of an AI Language Model's Impact on Medicine at Large and its Role in Pediatric Surgery. Xiao D, Meyers P, Upperman JS, Robinson JR. Xiao D, et al. J Pediatr Surg. 2023 Dec;58(12):2410-2415. doi: 10.1016/j.jpedsurg.2023.07.008. Epub 2023 Jul 20. J Pediatr Surg. 2023. PMID: 37544801 Review.
• The Expanding Role of ChatGPT (Chat-Generative Pre-Trained Transformer) in Neurosurgery: A Systematic Review of Literature and Conceptual Framework. Roman A, Al-Sharif L, Al Gharyani M. Roman A, et al. Cureus. 2023 Aug 15;15(8):e43502. doi: 10.7759/cureus.43502. eCollection 2023 Aug. Cureus. 2023. PMID: 37719492 Free PMC article. Review.
• A SWOT (Strengths, Weaknesses, Opportunities, and Threats) Analysis of ChatGPT in the Medical Literature: Concise Review. Gödde D, Nöhl S, Wolf C, Rupert Y, Rimkus L, Ehlers J, Breuckmann F, Sellmann T. Gödde D, et al. J Med Internet Res. 2023 Nov 16;25:e49368. doi: 10.2196/49368. J Med Internet Res. 2023. PMID: 37865883 Free PMC article. Review.
• Using ChatGPT in Medical Research: Current Status and Future Directions. Ruksakulpiwat S, Kumar A, Ajibade A. Ruksakulpiwat S, et al. J Multidiscip Healthc. 2023 May 30;16:1513-1520. doi: 10.2147/JMDH.S413470. eCollection 2023. J Multidiscip Healthc. 2023. PMID: 37274428 Free PMC article. Review.
• Artificial intelligence at the pen's edge: Exploring the ethical quagmires in using artificial intelligence models like ChatGPT for assisted writing in biomedical research. Sharma H, Ruikar M. Sharma H, et al. Perspect Clin Res. 2024 Jul-Sep;15(3):108-115. doi: 10.4103/picr.picr_196_23. Epub 2023 Dec 19. Perspect Clin Res. 2024. PMID: 39140014 Free PMC article. Review.
• Impact of Large Language Models on Medical Education and Teaching Adaptations. Zhui L, Yhap N, Liping L, Zhengjie W, Zhonghao X, Xiaoshu Y, Hong C, Xuexiu L, Wei R. Zhui L, et al. JMIR Med Inform. 2024 Jul 25;12:e55933. doi: 10.2196/55933. JMIR Med Inform. 2024. PMID: 39087590 Free PMC article.
• The Application of ChatGPT in Medicine: A Scoping Review and Bibliometric Analysis. Wu J, Ma Y, Wang J, Xiao M. Wu J, et al. J Multidiscip Healthc. 2024 Apr 18;17:1681-1692. doi: 10.2147/JMDH.S463128. eCollection 2024. J Multidiscip Healthc. 2024. PMID: 38650670 Free PMC article. Review.
• A Retrospective Comparison of Medication Recommendations Between a Cardiologist and ChatGPT-4 for Hypertension Patients in a Rural Clinic. Al Tibi G, Alexander M, Miller S, Chronos N. Al Tibi G, et al. Cureus. 2024 Mar 8;16(3):e55789. doi: 10.7759/cureus.55789. eCollection 2024 Mar. Cureus. 2024. PMID: 38586651 Free PMC article.
• ChatGPT in anesthesiology practice - A friend or a foe. Gupta B, Ahluwalia P, Gupta A, Mahaseth R. Gupta B, et al. Saudi J Anaesth. 2024 Jan-Mar;18(1):150-153. doi: 10.4103/sja.sja_336_23. Epub 2024 Jan 2. Saudi J Anaesth. 2024. PMID: 38313711 Free PMC article. No abstract available.

LinkOut - more resources

Full text sources.

• Taylor & Francis

• Citation Manager

NCBI Literature Resources

MeSH PMC Bookshelf Disclaimer

The PubMed wordmark and PubMed logo are registered trademarks of the U.S. Department of Health and Human Services (HHS). Unauthorized use of these marks is strictly prohibited.

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

ahmetbersoz/chatgpt-prompts-for-academic-writing

Folders and files.

Repository files navigation

✨ NEW UPDATE: Literature Review Generator

A Custom GPT for Literature Review Generator has been released. It efficiently parses PDF files of research publications, extracts key themes, and creates a literature review section for your academic publications.

TRY NOW: https://chat.openai.com/g/g-G3U8pZGwC-literature-review-generator

ChatGPT Prompts for Academic Writing

In this repository, this list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans. Whether you're a student, researcher, or academic professional, these prompts can help you hone your writing abilities and tackle your writing projects with confidence.

Use directly in: chat.openai.com

The list is regularly updated, so you can keep track of new prompts by following this repository.

TIPS: As there is a limit to the number of words that can be used in ChatGPT, you can input your text multiple times using the prompt "Read this [PARAPGRAPH]:" and then run your final prompt "Considering the above text...".

You can also use prompts splitter: chatgpt-prompt-splitter.jjdiaz.dev

BRAINSTORMING

Article sections, title/topic sentence, introduction, literature review.

NOTE: Be careful and double-check article existence. ChatGPT may generate fake references

Methodology

Experiments, future works, improving language, summarization, plan/presentation, working with documents (available only in gpt-4).

Upload a PDF file of a paper then:

Upload a PDF file of your paper then:

Upload PDF files of papers then:

Upload a figure image then:

Contributors 4

Grab your spot at the free arXiv Accessibility Forum

Help | Advanced Search

Computer Science > Information Retrieval

Title: can chatgpt write a good boolean query for systematic review literature search.

Abstract: Systematic reviews are comprehensive reviews of the literature for a highly focused research question. These reviews are often treated as the highest form of evidence in evidence-based medicine, and are the key strategy to answer research questions in the medical field. To create a high-quality systematic review, complex Boolean queries are often constructed to retrieve studies for the review topic. However, it often takes a long time for systematic review researchers to construct a high quality systematic review Boolean query, and often the resulting queries are far from effective. Poor queries may lead to biased or invalid reviews, because they missed to retrieve key evidence, or to extensive increase in review costs, because they retrieved too many irrelevant studies. Recent advances in Transformer-based generative models have shown great potential to effectively follow instructions from users and generate answers based on the instructions being made. In this paper, we investigate the effectiveness of the latest of such models, ChatGPT, in generating effective Boolean queries for systematic review literature search. Through a number of extensive experiments on standard test collections for the task, we find that ChatGPT is capable of generating queries that lead to high search precision, although trading-off this for recall. Overall, our study demonstrates the potential of ChatGPT in generating effective Boolean queries for systematic review literature search. The ability of ChatGPT to follow complex instructions and generate queries with high precision makes it a valuable tool for researchers conducting systematic reviews, particularly for rapid reviews where time is a constraint and often trading-off higher precision for lower recall is acceptable.

Submission history

Access paper:.

• Other Formats

References & Citations

• Google Scholar
• Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

• Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

• Learn Chat GPT
• Learn Chat GPT (Advanced)

Step-by-Step Guide: 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.

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

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.

By signing up, you agree to our User Agreement and Privacy Policy & Cookie Statement .

Emerging AI Tools for Literature Review: Cite AI-generated Text

• Comparison of GenAI Tools
• Comparison of LLMs
• Limitations of GenAI
• Cite AI-generated Text
• Cite AI-generated Images
• Prompting Tips
• Workshop PPT (Apr 2024)

This page covers:

Use of AI in Scholarly Publishing Cite AI-generated Text Cite AI-generated Images

Citing AI Tools & AI-generated Text

At present, most citation styles do not have specific guidelines for referencing ChatGPT or other GenAI tools. The following are some available guidelines or recommendations from a few citation styles.

Guideline from APA:

• How to cite ChatGPT  - APA Style Blog (updated on Feb 23, 2024)  

Suggested practices:

1. Cite AI-generated text

• cite the content as  software or algorithm's output   (rather than personal communication as there's no actual person communicating)
• describe how you used ChatGPT or other AI models in the Method or Introduction of your work
• include the prompt used and any relevant  generated text in your paper
• for long responses, consider including them in an appendix

2. Cite AI model (e.g. ChatGPT, Claude)

• cite the model or tool as software

According to the IEEE  Submission and Peer Review Policies ->  Guidelines for Artificial Intelligence (AI)-Generated Text

"The use of content generated by artificial intelligence (AI) in an article (including but not limited to text, figures, images, and code) shall be disclosed in the acknowledgments section of any article submitted to an IEEE publication. The AI system used shall be identified, and specific sections of the article that use AI-generated content shall be identified and accompanied by a brief explanation regarding the level at which the AI system was used to generate the content.

The use of AI systems for editing and grammar enhancement is common practice and, as such, is generally outside the intent of the above policy. In this case, disclosure as noted above is recommended."

We suggest referring to AI-generated content as  Software  in IEEE style. 

Guideline from MLA:

• How do I cite Generative AI in MLA Style?   - MLA blog (March 17, 2023)

General advice:

• Cite generative AI tools whenever you paraphrase, quote, or incorporate into your own work any content (text, image, data, or other)
• Acknowledge functional uses (e.g. editing, translating) in a note or your text.
• Examine secondary sources cited by AI tools carefully.

Format & Examples:

• Use MLA's template   for flexibility in citations, adapting as needed.

Chicago style

Guideline from Chicago:

• Recommendations for Citing ChatGPT & other tools  - Chicago Style Blog
• Credit tools when using generated text, e.g. "The following was generated by XXX model or tool". 
• Treat conversation as personal communication (see CMOS 14.214 and 15.53).
• Indicate in the text or at the end of the note if AI-generated text is edited (e.g. “edited for style and content”).
• Do not cite the tool in reference list unless a public URL is available; include the non-sharable chat in Appendix instead. 

Format for a formal citation & Examples:

• In-text citation: 
• Reference list (when public URL is available):
• << Previous: Citing GenAI
• Next: Cite AI-generated Images >>
• Last Updated: Aug 15, 2024 5:00 PM
• URL: https://libguides.hkust.edu.hk/AI-tools-literature-review

How to cite ChatGPT

Use discount code STYLEBLOG15 for 15% off APA Style print products with free shipping in the United States.

We, the APA Style team, are not robots. We can all pass a CAPTCHA test , and we know our roles in a Turing test . And, like so many nonrobot human beings this year, we’ve spent a fair amount of time reading, learning, and thinking about issues related to large language models, artificial intelligence (AI), AI-generated text, and specifically ChatGPT . We’ve also been gathering opinions and feedback about the use and citation of ChatGPT. Thank you to everyone who has contributed and shared ideas, opinions, research, and feedback.

In this post, I discuss situations where students and researchers use ChatGPT to create text and to facilitate their research, not to write the full text of their paper or manuscript. We know instructors have differing opinions about how or even whether students should use ChatGPT, and we’ll be continuing to collect feedback about instructor and student questions. As always, defer to instructor guidelines when writing student papers. For more about guidelines and policies about student and author use of ChatGPT, see the last section of this post.

Quoting or reproducing the text created by ChatGPT in your paper

If you’ve used ChatGPT or other AI tools in your research, describe how you used the tool in your Method section or in a comparable section of your paper. For literature reviews or other types of essays or response or reaction papers, you might describe how you used the tool in your introduction. In your text, provide the prompt you used and then any portion of the relevant text that was generated in response.

Unfortunately, the results of a ChatGPT “chat” are not retrievable by other readers, and although nonretrievable data or quotations in APA Style papers are usually cited as personal communications , with ChatGPT-generated text there is no person communicating. Quoting ChatGPT’s text from a chat session is therefore more like sharing an algorithm’s output; thus, credit the author of the algorithm with a reference list entry and the corresponding in-text citation.

When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).

OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat

You may also put the full text of long responses from ChatGPT in an appendix of your paper or in online supplemental materials, so readers have access to the exact text that was generated. It is particularly important to document the exact text created because ChatGPT will generate a unique response in each chat session, even if given the same prompt. If you create appendices or supplemental materials, remember that each should be called out at least once in the body of your APA Style paper.

When given a follow-up prompt of “What is a more accurate representation?” the ChatGPT-generated text indicated that “different brain regions work together to support various cognitive processes” and “the functional specialization of different regions can change in response to experience and environmental factors” (OpenAI, 2023; see Appendix A for the full transcript).

Creating a reference to ChatGPT or other AI models and software

The in-text citations and references above are adapted from the reference template for software in Section 10.10 of the Publication Manual (American Psychological Association, 2020, Chapter 10). Although here we focus on ChatGPT, because these guidelines are based on the software template, they can be adapted to note the use of other large language models (e.g., Bard), algorithms, and similar software.

The reference and in-text citations for ChatGPT are formatted as follows:

• Parenthetical citation: (OpenAI, 2023)
• Narrative citation: OpenAI (2023)

Let’s break that reference down and look at the four elements (author, date, title, and source):

Author: The author of the model is OpenAI.

Date: The date is the year of the version you used. Following the template in Section 10.10, you need to include only the year, not the exact date. The version number provides the specific date information a reader might need.

Title: The name of the model is “ChatGPT,” so that serves as the title and is italicized in your reference, as shown in the template. Although OpenAI labels unique iterations (i.e., ChatGPT-3, ChatGPT-4), they are using “ChatGPT” as the general name of the model, with updates identified with version numbers.

The version number is included after the title in parentheses. The format for the version number in ChatGPT references includes the date because that is how OpenAI is labeling the versions. Different large language models or software might use different version numbering; use the version number in the format the author or publisher provides, which may be a numbering system (e.g., Version 2.0) or other methods.

Bracketed text is used in references for additional descriptions when they are needed to help a reader understand what’s being cited. References for a number of common sources, such as journal articles and books, do not include bracketed descriptions, but things outside of the typical peer-reviewed system often do. In the case of a reference for ChatGPT, provide the descriptor “Large language model” in square brackets. OpenAI describes ChatGPT-4 as a “large multimodal model,” so that description may be provided instead if you are using ChatGPT-4. Later versions and software or models from other companies may need different descriptions, based on how the publishers describe the model. The goal of the bracketed text is to briefly describe the kind of model to your reader.

Source: When the publisher name and the author name are the same, do not repeat the publisher name in the source element of the reference, and move directly to the URL. This is the case for ChatGPT. The URL for ChatGPT is https://chat.openai.com/chat . For other models or products for which you may create a reference, use the URL that links as directly as possible to the source (i.e., the page where you can access the model, not the publisher’s homepage).

Other questions about citing ChatGPT

You may have noticed the confidence with which ChatGPT described the ideas of brain lateralization and how the brain operates, without citing any sources. I asked for a list of sources to support those claims and ChatGPT provided five references—four of which I was able to find online. The fifth does not seem to be a real article; the digital object identifier given for that reference belongs to a different article, and I was not able to find any article with the authors, date, title, and source details that ChatGPT provided. Authors using ChatGPT or similar AI tools for research should consider making this scrutiny of the primary sources a standard process. If the sources are real, accurate, and relevant, it may be better to read those original sources to learn from that research and paraphrase or quote from those articles, as applicable, than to use the model’s interpretation of them.

We’ve also received a number of other questions about ChatGPT. Should students be allowed to use it? What guidelines should instructors create for students using AI? Does using AI-generated text constitute plagiarism? Should authors who use ChatGPT credit ChatGPT or OpenAI in their byline? What are the copyright implications ?

On these questions, researchers, editors, instructors, and others are actively debating and creating parameters and guidelines. Many of you have sent us feedback, and we encourage you to continue to do so in the comments below. We will also study the policies and procedures being established by instructors, publishers, and academic institutions, with a goal of creating guidelines that reflect the many real-world applications of AI-generated text.

For questions about manuscript byline credit, plagiarism, and related ChatGPT and AI topics, the APA Style team is seeking the recommendations of APA Journals editors. APA Style guidelines based on those recommendations will be posted on this blog and on the APA Style site later this year.

Update: APA Journals has published policies on the use of generative AI in scholarly materials .

We, the APA Style team humans, appreciate your patience as we navigate these unique challenges and new ways of thinking about how authors, researchers, and students learn, write, and work with new technologies.

American Psychological Association. (2020). Publication manual of the American Psychological Association (7th ed.). https://doi.org/10.1037/0000165-000

Related and recent

Comments are disabled due to your privacy settings. To re-enable, please adjust your cookie preferences.

APA Style Monthly

Subscribe to the APA Style Monthly newsletter to get tips, updates, and resources delivered directly to your inbox.

Welcome! Thank you for subscribing.

APA Style Guidelines

Browse APA Style writing guidelines by category

• Abbreviations
• Bias-Free Language
• Capitalization
• In-Text Citations
• Italics and Quotation Marks
• Paper Format
• Punctuation
• Research and Publication
• Spelling and Hyphenation
• Tables and Figures

Full index of topics

ChatGPT Prompts for Academic Writing

Did you know that ChatGPT is a powerful tool for academic writing? While it can be a valuable resource, let’s make one thing clear: we’re not talking about using the chatbot to complete assignments for you. Instead, you can use AI at various stages of the writing process, from brainstorming ideas to refining and editing your work.

You’ll find effective ChatGPT prompts for research papers, proposals, case studies, and more in this article.

• 🔝 10 Most Useful Prompts
• 🔎 Prompts for Research Paper
• 📝 Prompts for Proposal
• 📊 Prompts for Case Study
• 🔬 Prompts for Scientific Writing
• ✍️ Prompts for Report Writing
• 🤖 How to Write ChatGPT Prompts

🔗 References

🔝 10 most useful chatgpt prompts for academic writing.

Effective prompts can help you release the full potential of ChatGPT for academic writing. Here are some prompts that will help you handle the most frequent academic tasks, like choosing a topic or summarizing texts:

• Suggest 10 research topics in the field of [subject].
• Generate 10 academic research questions about [topic].
• Create an outline for a research paper about [topic].
• Provide examples of thesis statements on [topic].
• Summarize this article’s main points: [text of the article].
• Simplify this text to make it easier to understand: [text].
• Rewrite this paragraph in academic language: [paragraph].
• Correct grammar and spelling mistakes in this paragraph: [text].
• Provide 5 arguments for/against the following claim: [claim].
• Improve the coherence and clarity of my paper: [text].

🔎 ChatGPT Prompts for Research Paper Writing

A research paper is a common type of academic writing that involves gathering information on the topic and presenting unique findings. No doubt, writing a research paper takes some time and effort. However, ChatGPT can become your helpful assistant.

Choosing a Research Topic & Question

The first step of writing a research paper is to choose a topic and formulate a research question. Making your topic original, manageable, clear, and impactful is important. Since there are a lot of aspects to consider, you can ask ChatGPT to generate the most suitable topic ideas or to provide feedback on the topics you brainstormed yourself.

Here are some prompt examples for research topics and questions:

If you don’t want to bother with ChatGPT prompts, try our free research question maker to create a compelling research question in a few clicks!

Finding Information & Sources

Instead of spending hours browsing the Internet or wandering around your school library, you can use ChatGPT to find information for your research . Ask the chatbot to recommend online sources dedicated to your research topic, and it will provide you with a list of relevant websites, journals, and databases. You can even ask ChatGPT to give you a list of specific references to use. However, note that sometimes ChatGPT suggests outdated or non-existent sources, so always double-check.

Have a look at these prompts that can help find literature for your research:

Organizing Ideas

If you need help organizing ideas for your research paper, ChatGPT is a great solution. You ask the chatbot to create an outline for an entire writing or to structure a separate part, such as an introduction or literature review. Moreover, you can use ChatGPT to generate transition phrases and sentences to ensure coherence and a smooth paper flow.

Do you want to know more prompts for organizing your ideas? Check out our examples!

Revising and Proofreading

After working many days on your research paper, you may lose freshness of vision. To get detailed feedback on your writing, you can ask ChatGPT to check it for mistakes and identify what can be improved. One useful tip is to specify what the chatbot should focus on, such as spelling, punctuation, grammar, or academic language.

Check out these proofreading prompt examples:

📝 ChatGPT Prompts for Proposal Writing

Proposal writing is common among researchers, business professionals, and students. This paper aims to persuade the target audience to approve or support the proposed project or research. Writing a persuasive proposal can be time-consuming, so why not use ChatGPT as a help?

Brainstorming Innovative Project Ideas

ChatGPT can help you overcome writer’s block and suggest topics for your proposal writing. For example, you can identify a problem and ask the chatbot to come up with several solutions. Moreover, you can use AI to identify a research gap in the scientific literature on the topic of your interest.

Here are more prompts for brainstorming proposal ideas:

Structuring Your Proposal

Every successful proposal starts with an effective plan. If you haven’t written a proposal before, you can use ChatGPT to write a detailed outline for an entire paper or organize specific parts, such as literature review, timing, or budget.

For more inspiration, consider these prompt ideas:

Strengthening Your Argument

Proposal writing aims to convince the target audience to support your project. If you need ideas on how to make your paper more persuasive, try out ChatGPT. For example, you may ask the bot to highlight the importance of your paper for society or science or write a passage that presents you as a trustworthy expert.

Check out some prompts for strengthening your proposal :

Meeting Proposal Guidelines

Sometimes, the requirements we get from our school or professor are unclear or simply overwhelming. To ensure you meet all the guidelines, you may share the requirements with ChatGPT and let the bot check the proposal for you.

Here are some prompts you can use:

📊 ChatGPT Prompts for Case Study Writing

Usually, students are asked to analyze case studies to demonstrate their theoretical knowledge and apply it in practice. However, some professors give students a task to create their own case studies to test their creativity and critical thinking. Whether you’re a teacher or a student, the following ChatGPT prompts will be helpful when writing a case study.

Identifying a Case Study Subject

Choosing a case study topic can be a daunting task. It usually requires the writer to read about current events, consult academic journals, or talk to experts. Luckily, ChatGPT can make the topic selection much easier and ensure your case study is engaging and relevant.

These are some prompts you can use when choosing a case study subject:

Gathering and Analyzing Data

The most time-consuming step when writing a case study is gathering data. You need to analyze databases, industry websites, and previous case studies. Moreover, you might conduct an interview to make your case study more insightful. If you want to optimize your time when gathering data for your paper, you should try ChatGPT.

Here are some helpful prompts for collecting and analyzing information:

Structuring and Writing

You might be surprised to learn how many opportunities ChatGPT offers when structuring your case study. For example, you can ask the bot to write a detailed outline. What is more, ChatGPT can suggest engaging hooks for your introduction and provide recommendations on presenting your data.

Check out some prompt examples:

Other Helpful Prompts

What else can ChatGPT do to help you write an outstanding case study? For example, you may ask the chatbot to provide case study examples on your topic for some inspiration. Moreover, you can ask the bot to list the most common case study writing mistakes you should avoid.

Here are some bonus prompts you should try:

We also recommend you use our free case study answer generator if you need help analyzing a case study.

🔬 ChatGPT Prompts for Scientific Writing

As you might already know, scientific writing is characterized by precision and clarity. All scientific articles follow a specific structure: abstract, introduction, literature review , methodology, results, discussion, and conclusion. The following section will discuss how ChatGPT can assist you with each of these parts.

Prompts for Title, Abstract, & Keywords

The title, abstract, and keywords form a first impression of your article. ChatGPT can assist with these parts by generating engaging titles based on the research content and summarizing key points into a clear abstract. You may also ask the chatbot to suggest relevant keywords that will improve the online visibility of your article.

Creating a concise and accurate abstract for your research paper is even easier with our free AI abstract generator !

Prompts for Introduction

A scientific article’s introduction should include background information on the topic, research gap, your research question, hypothesis, methodology overview, and significance of the article. You can ask ChatGPT to create an introduction outline to avoid getting lost in all these elements.

For you, we prepared some effective prompts:

You can also use our free research introduction maker to write a compelling opening section for your paper!

ChatGPT Prompts for Literature Review

A literature review is a critical component that provides an overview of other studies on the topic. Writing a well-structured literature review may take a lot of time and effort, but ChatGPT can help make this process more productive. For example, the chatbot can list relevant literature, summarize long sources , and identify key themes.

Here are some prompt ideas:

We also suggest you try our free key points generator to save time reading through a vast amount of literature.

Prompts for Methodology

The methodology section explains how your research was carried out and lets readers decide if your approach is trustworthy. To save time while writing this section, you can use ChatGPT to find the most suitable research tools or generate descriptions of methods.

Try out these useful prompts:

Prompts for Results & Discussion

In the results section of a scientific article, you should clearly and concisely present your key findings. As for the discussion section, it should interpret your results and link them to current knowledge on the topic. ChatGPT can help you analyze your data, suggest possible explanations of the results, and connect your findings to the existing literature.

Here are more prompt ideas for the results section:

ChatGPT Prompts for Conclusion

The main purpose of the conclusion in a scientific article is to present the implications of your research and highlight the significance of your paper. ChatGPT can be a great assistant in summarizing and paraphrasing the key findings and generating ideas on future research directions.

These are helpful prompts you can use for a conclusion:

You can also use our free conclusion generator to write an effective closing section for your article.

✍️ ChatGPT Prompts for Report Writing

The purpose of report writing is to present information on a particular topic. Reports allow students to demonstrate their understanding of a subject and their analytical skills. If you need help writing a report, try the following ChatGPT prompts.

Writing Executive Summary

Usually, report writing starts with an executive summary , which provides an overview of the main findings of a report. You may ask the bot to generate an engaging opening sentence or summarize your key points.

Here are more prompts you can use for an executive summary:

Designing Surveys and Interviews

When writing a report, you might need to collect some primary data. It is the type of information you gather with the help of surveys, questionnaires, or interviews. You may ask ChatGPT to generate a questionnaire on a particular topic or a set of questions for an interview.

Check out these prompts for designing interviews and surveys:

Creating Visual Aids

You should consider adding some visuals to make your report more engaging and easier to understand. Unfortunately, the free version of ChatGPT can only generate tables for you, while ChatGPT Plus can also create schemes and graphs. However, you can still ask the free bot for recommendations, such as what pictures to choose or colors to use for your infographics.

Check out some prompt ideas:

Generating Recommendations

Recommendations are practical steps or suggestions presented in the conclusion. ChatGPT can help ensure your recommendations are innovative, actionable, and realistic. You may simply ask the chatbot to generate recommendations based on your findings or provide feedback on your ideas.

These are the prompts you should try for the recommendations part:

Tailoring Language and Tone

To maximize the impact of your report, you should adjust the language and tone of your paper to the audience. Always remember your readers’ level of expertise and readiness to support your ideas.

Here are some prompts that will help tailor the tone and language of your report:

🤖 How to Write ChatGPT Prompts for Academic Writing

The ChatGPT prompts we’ve explored can undoubtedly empower you to craft impactful academic papers. However, if you want even more tailored responses from the bot, you should learn how to make effective prompts yourself.

Be Specific

To get the best results using ChatGPT, clearly define the task, include only relevant details, and avoid ambiguity.

Compare these prompt examples:

❌ Bad prompt

✅ Good prompt

Ask ChatGPT to Act as If…

To make ChatGPT generate more relevant responses, you may start your prompts with “Act as if…” The bot can play the role of anyone whose perspective you want to consider: a professor, a psychotherapist, an experienced manager, a high school student, and so on. A small prompt example: “Act as if you’re a strict English teacher and say if my poetry analysis is detailed enough.”

Specify Your Output Format

Don’t forget to specify the format of the content you expect to receive from ChatGPT. The bot can generate summaries, stories, dialogues, ordered and unordered lists, tables, and even code. After describing your task, you may add to the prompt, “Present this in the form of…”

Use “Do” and “Don’t”

Don’t expect AI to read your mind. Instead, tell ChatGPT directly what you want and don’t want in your response. Here is how you can add dos and don’ts in your prompt: “Suggest 10 controversial essay topics. Include original and creative topics, but don’t include topics about abortion, euthanasia, gun control, and capital punishment.”

Use Examples

If you have an example of a sentence or a paragraph you want ChatGPT’s output to resemble, add it to your prompt. This is a simple solution to improving the quality of the results. For instance, you can structure your prompt as follows: “Generate an introduction for an essay about climate change. Use this introduction as an example [introduction example].”

Consider the Tone and Audience

Let ChatGPT know about your audience and the tone you’d like to set. For example, a prompt “I plan to deliver an oral presentation on [topic]. Give me ideas for a speech that is [tone] and is appropriate for [the audience]” is way more effective than a simple “Give me speech topic ideas on [topic].”

Work Together with AI

Imagine that ChatGPT is your teammate, and you’re working on your academic writing together. To improve AI outputs, give your feedback, for example, on what you liked and what can be improved. Finally, remember that you can always ask the chatbot for advice on improving your prompts or even generating them for you.

One more tip: whenever you integrate the content produced by ChatGPT into your writing, don’t forget to check it for AI to ensure your paper keeps its human touch. Our free Chat GPT essay detector will help you with this!

In conclusion, unraveling the power of ChatGPT for academic writing can be a game-changer, but only if you use AI ethically and craft clear, effective prompts. If you like our ideas, check out other articles about using ChatGPT for educational purposes:

• How to Get ChatGPT to Write an Essay
• How to Use AI for Literature Review Writing
• ## Best AI Tools for Students
• How to Not Get Caught Using ChatGPT
• ChatGPT Prompts for Academic Writing | GitHub
• How to Write Persuasive Proposals With ChatGPT | Make Use Of
• Can ChatGPT Be Used as a Proofreader? | Make Use Of
• We Used ChatGPT to Generate Citations | Indiana Daily Student
• Should I Use ChatGPT to Write My Essays? | Harvard Summer School
• How to Make ChatGPT Provide Sources and Citations | ZDNET
• How to Use ChatGPT to Make Charts and Tables | ZDNET
• How to Use ChatGPT to Write a Literature Review with Prompts | Florida International University
• How to Write Better ChatGPT Prompts in 5 Steps | ZDNET
• Prompt Literacy in Academics | University of Michigan
• Getting Started with Prompts for Text-based Generative AI Tools | Harvard University
• ChatGPT in Academic Writing: Maximizing Its Benefits and Minimizing the Risks | Indian Journal of Ophthalmology
• 12 Best ChatGPT Prompts for Academic Writing Assistance in 2024 | Geeksforgeeks
• ChatGPT & AI Literacy Toolbox: Images, Writing, & Prompts | Florida International University
• Share to Facebook
• Share to LinkedIn

How to Use ChatGPT to Write a Literature Review With Prompts

Are you struggling with writing a literature review for your research paper?

Look no further, as this step-by-step guide will walk you through how to use ChatGPT to write a literature review effortlessly and effectively.

Leveraging ChatGPT for Conducting Meta-Analysis in Research

12 ChatGPT Prompts for Text Analysis

Defining Research Objectives Using ChatGPT

For example, by inputting a prompt related to your research topic, ChatGPT can generate text that reviews prior research and highlights pertinent literature.

Although ChatGPT can assist in synthesizing extensive information and developing a clear outline, it should be used as a supplementary tool rather than a substitute for thorough human analysis.

Identifying Relevant Keywords and Search Terms

For example, by providing a summary of your research question to ChatGPT, the AI can generate a list of relevant keywords.

This method is particularly advantageous for systematic reviews or for those unfamiliar with specific academic terminology.

Developing an Initial Literature Review Outline

To effectively use ChatGPT in creating an initial literature review outline, leverage its capability to generate content based on specific prompts.

This initial outline provides a useful framework for organizing your review and identifying key areas to address. Researchers can further refine and expand this outline as they progress with their research to ensure it aligns with their specific research questions and current research developments.

Step 1: Familiarize Yourself with ChatGPT

To get started, visit the official website of ChatGPT at chat.openai.com

Step 2: Understanding Prompts

Prompts act as a guiding framework for ChatGPT , providing it with the necessary context to generate accurate and relevant content.

Step 3: Crafting an Effective Prompt

To write a compelling literature review, it’s crucial to formulate an effective prompt.

Example: Prompt # 1

Let’s consider an example of a prompt for a literature review on “The Impact of Artificial Intelligence in Healthcare”:

Example: Prompt # 2

10 ChatGPT Prompts for Job Applications

Step 4: Interacting with ChatGPT

Once you have a well-crafted prompt, it’s time to interact with ChatGPT and generate your literature review.

Output provided by the ChatGPT

Literature Review

Definition of Variables:

Hypothesis 1 (H1): Stress has a positive influence on digital hoarding. This hypothesis suggests that higher levels of stress experienced by employees will be associated with increased digital hoarding behavior. Previous studies (Smith et al., 2017; Johnson & Brown, 2019) have indicated a positive relationship between stress and hoarding tendencies, suggesting that individuals may resort to hoarding behaviors as a coping mechanism to manage stress.

Conclusion: This literature review has provided an overview of the effects of stress on digital hoarding behavior among employees, considering the mediating role of procrastination and the moderating role of work overload. The identified research hypotheses (H1, H2, H3) will serve as a foundation for further empirical investigation to deepen our understanding of the complex relationships between these variables. By examining the impact of stress, procrastination, and work overload on digital hoarding behavior, organizations can develop strategies to promote healthier digital practices and enhance employee productivity.

Roberts, L. D., & Zomer, A. C. (2016). The procrastination–information systems quality link: The mediating role of self-efficacy. Computers in Human Behavior, 65, 167-176.

Step 5: Refining and Polishing

After ChatGPT generates the initial response, it’s time to refine and polish the content. Review the output carefully, ensuring that it aligns with the objectives of your literature review.

Note: The literature review that you would get is plagiarism-free. This is another benefit of using chatgpt to write literature review.

How to Use ChatGPT to Write Code: A Software Developer’s Guide

Step 6: Iterative Process

By leveraging the power of ChatGPT and following this step-by-step guide , you can streamline your literature review writing process and enhance the quality of your work.

Other articles

Please read through some of our other articles with examples and explanations if you’d like to learn more.

Related Posts

How are style manuals updated, difference between “almost” and “nearly” in scientific writing, timeline for writing a research paper in a month, how to translate text using chatgpt | prompts and examples, how to paraphrase text using chatgpt | prompts and examples, how to write a 10 and 20-page research paper in one night, how to create table of contents for research paper, how to write a synopsis for research: a step-by-step guide, 4 research proposal examples | proposal sample, research paper outline template: examples of structured research paper outlines.

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

The best AI for coding, and a bunch that failed miserably

I've been around technology for long enough that very little excites me, and even less surprises me. But shortly after Open AI's ChatGPT was released, I asked it to write a WordPress plugin for my wife's e-commerce site . When it did, and the plugin worked, I was indeed surprised.

That was the beginning of my deep exploration into chatbots and AI-assisted programming. Since then, I've subjected 10 large machine models (LLMs) to four real-world tests.

How to use ChatGPT to write:  Resumes  |  Excel formulas  |  Essays  |  Cover letters  

Unfortunately, not all chatbots can code alike. It's been 18 months since that first test, and even now, five of the 10 LLMs I tested can't create working plugins. 

In this article, I'll show you how each LLM performed against my tests. There are two chatbots I recommend you use, but they cost $20/month. The free versions of the same chatbots do well enough that you could probably get by without paying. But the rest, whether free or paid, are not so great. I won't risk my programming projects with them or recommend that you do until their performance improves.

Also:  How I test an AI chatbot's coding ability - and you can too

I've written a lot about using AIs to help with programming . Unless it's a small, simple project, like my wife's plugin, AIs can't write entire apps or programs. But they excel at writing a few lines and are not bad at fixing code. 

Rather than repeat everything I've written, go ahead and read this article:  How to use ChatGPT to write code: What it can and can't do for you .

If you want to understand my coding tests, why I've chosen them, and why they're relevant to this review of the 10 LLMs, read this article:  How I test an AI chatbot's coding ability - and you can too .  

Let's start with a comparative look at how the chatbots performed:

Next, let's look at each chatbot individually. I'll discuss nine chatbots, even though the above chart shows 10 LLMs. The results for GPT-4 and GPT-4o are both included in ChatGPT Plus. Ready? Let's go.

ChatGPT Plus

Best overall ai chatbot for coding.

• Passed all tests
• Solid coding results
• Hallucinations
• No Windows app yet
• Sometimes uncooperative
• Price: $20/mo
• LLM: GPT-4o, GPT-4, GPT-3.5
• Desktop browser interface: Yes
• Dedicated Mac app: Yes
• Dedicated Windows app: No
• Multi-factor authentication: Yes
• Tests passed: 4 of 4

ChatGPT Plus  with GPT-4 and GPT-4o passed all my tests. One of my favorite features is the availability of a dedicated app. When I test web programming, I have my browser set on one thing, my IDE open, and the ChatGPT Mac app running on a separate screen.

Also:  I put GPT-4o through my coding tests and it aced them - except for one weird result

In addition,  Logitech's Prompt Builder , which pops up using a mouse button, can be set up to use the upgraded GPT-4o and connect to your OpenAI account, making it a simple thumb-tap to run a prompt, which is very convenient.

The only thing I didn't like was that one of my GPT-4o tests resulted in a dual-choice answer, and one of those answers was wrong. I'd rather it just gave me the correct answer. Even so, a quick test confirmed which answer would work. But that was a bit annoying. I didn't have that issue in GPT-4, so for now, that's the LLM setting I use with ChatGPT when coding.

Perplexity Pro

Best ai chatbot for llm testing.

• Multiple LLMs
• Search criteria displayed
• Good sourcing
• Email-only login
• No desktop app
• LLM: GPT-4o, Claude 3.5 Sonnet, Sonar Large, Claude 3 Opus, Llama 3.1 405B
• Dedicated Mac app: No
• Multi-factor authentication: No

I seriously considered listing  Perplexity Pro  as the best overall AI chatbot for coding, but one failing kept it out of the top slot: how you log in. Perplexity doesn't use username/password or passkey, and doesn't have multi-factor authentication. All it does is email you a login pin. The AI also doesn't have a separate desktop app, as ChatGPT does for Macs.

What sets Perplexity apart from other tools is that it can run multiple LLMs. While you can't set an LLM for a given session, you can easily go into the settings and choose the active model.

Also:  Can Perplexity Pro help you code? It aced my programming tests - thanks to GPT-4

For programming, you'll probably want to stick to GPT-4o, because that aced all our tests. But it might be interesting to cross-check code across the different LLMs. For example, if you have GPT-4o write some regular expression code, you might consider switching to a different LLM to see what that LLM thinks of the generated code.

As we'll see below, most LLMs are unreliable, so don't take the results as gospel. However, you can use the results to give you more things to check your original code. It's sort of like an AI-driven code review.

Just don't forget to switch back to GPT-4o.

ChatGPT Free

Best free ai chatbot for coding.

• Passed most tests
• Prompt throttling
• Could cut you off in the middle of whatever you're working on
• Price: Free
• LLM: GPT-4o, GPT-3.5
• Tests passed: 3 of 4 in GPT-3.5 mode

ChatGPT  is available to anyone for free. While both the Plus and free versions support GPT-4o, which passed all my programming tests, there are limitations when using the free app.

OpenAI treats free ChatGPT users as if they're in the cheap seats. If traffic is high or the servers are busy, the free ChatGPT will only make GPT-3.5 available to free users. The tool will only allow you a certain number of queries before it downgrades or shuts you off.

Also:  How to use ChatGPT: What you need to know now

I've had several occasions when the free version of ChatGPT effectively told me I'd asked too many questions.

ChatGPT is a great tool, as long as you don't mind getting shut down sometimes. Even GPT-3.5 did better on the tests than all the other chatbots, and the test it failed was for a fairly obscure programming tool produced by a lone programmer in Australia.

So, if budget is important to you and you can wait when cut off, go for ChatGPT free.

Perplexity Free

Best free ai chatbot for coding and research.

• Range of research tools
• Limited to GPT-3.5
• Throttles prompt results
• LLM: GPT-3.5
• Tests passed: 3 of 4

I'm threading a pretty fine needle here, but because Perplexity AI' s free version is based on GPT-3.5, the test results were measurably better than the other AI chatbots.

Also: 5 reasons why I prefer Perplexity over every other AI chatbot

From a programming perspective, that's pretty much the whole story. But from a research and organization perspective, my ZDNET colleague Steven Vaughan-Nichols prefers Perplexity over the other AIs.

He likes how Perplexity provides more complete sources for research questions, how it cites its sources, how it organizes the replies, and how it provides questions to further searches.

So if you're programming, but also doing other research, consider the free version of Perplexity.

Chatbots to avoid for programming help

I tested nine chatbots, and four passed most of my tests. The other chatbots, including a few pitched as great for programming, each only passed one of my tests -- and Microsoft's Copilot didn't pass any .

I'm mentioning them here because people will ask, and I did test them thoroughly. Some of them do just fine for other work, so I'll point you to their more general reviews if you're just curious about how they function.

Meta AI is Facebook's general-purpose AI. As you can see above, it failed three of our four tests. 

Also:  How to get started with Meta AI in Facebook, Instagram, and more

The AI did generate a nice user interface but with zero functionality. And it did find my annoying bug, which is a fairly serious challenge. Given the specific knowledge required to find the bug, I was surprised it choked on a simple regular expression challenge. But it did.

Meta Code Llama

Meta Code Llama is Facebook's AI designed specifically for coding help. It's something you can download and install on your server. I tested it running on a Hugging Face AI instance.

Also:  Can Meta AI code? I tested it against Llama, Gemini, and ChatGPT - it wasn't even close

Weirdly, even though both Meta AI and Meta Code Llama choked on three of four of my tests, they choked on different problems. AIs can't be counted on to give the same answer twice, but this result was a surprise. We'll see if that changes over time.

Claude 3.5 Sonnet

Anthropic claims the 3.5 Sonnet version of its Claude AI chatbot is ideal for programming. After failing all but one test, I'm not so sure.

If you're not using it for programming, Claude may be a better choice than the free version of ChatGPT. 

Also:  4 things Claude AI can do that ChatGPT can't

My ZDNET colleague Maria Diaz reports that Claude can handle uploaded files, process more words than the free version of ChatGPT, provide information roughly a year more current than GPT-3.5, and access websites.

Gemini Advanced

Gemini Advanced is Google's $20 pro version of its Gemini (formerly Bard) chatbot. I expected the tool to do better than one out of four. Interestingly, it passed the one test that every AI other than GPT-4/4o failed -- knowledge of that fairly obscure programming language produced by one programmer in Australia.

Also:  3 ways Gemini Advanced beats other AI assistants, according to Google

So, if it knew that language, why couldn't it handle basic regular expressions or other first-year programming student problems?

Microsoft Copilot

You'd think the company with the "Developers! Developers! Developers!" mantra in its DNA would have an AI that does better on the programming tests. Microsoft produces some of the best coding tools on the planet. And yet, Copilot did badly .

Also:  What are Microsoft's different Copilots? Here are the differences and how you can use them

The one positive thing is that Microsoft always learns from its mistakes. So, I'll check back later and see if this result improves.  

It's only a matter of time

The results of my tests were fairly surprising, especially given the big investments of Microsoft and Google. But this area of innovation is improving at warp speed , so we'll be back with updated tests and results over time. Stay tuned.

Have you used any of these AI chatbots for programming? What has your experience been? Let us know in the comments below.

You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter , and follow me on Twitter/X at @DavidGewirtz , on Facebook at Facebook.com/DavidGewirtz , on Instagram at Instagram.com/DavidGewirtz , and on YouTube at YouTube.com/DavidGewirtzTV .

If these chatbots could talk: The most popular ways people are using AI tools

Ai scientist: 'we need to think outside the large language model box', lost in translation: ai chatbots still too english-language centric, stanford study finds.