Skip to Main Content

Research with Generative AI: Overview

What is generative AI?

Generative AI (GenAI) is a type of artificial intelligence that produces content such as text, images, or music. GenAI does not actually understand the content it produces. Instead, it makes predictions about the relationships between words, images, and sounds. 

GenAI is trained on datasets, called large language models, that allow it to know how grammar, vocabulary, and style contribute to text. It mimics the language structures learned from the data to create coherent sentences.

Machine learning makes it possible for computers to learn from large datasets without being explicitly programmed to do so. This means that performance is continually improved through more data exposure.

Generative AI Research Tools

Best Uses




Useful for primary and secondary sources, translate into or out of English for best results

ChatPDF: upload PDF, limited to 2 PDFs a day at 120 pages each

ChatGPT: copy and paste text, limited to 4,000 tokens

Searching for scholarly articles

Semantic scholar: use author, title, or DOI for searching; English-language focused; narrow book coverage; patents not included

Consensus: use question form for searching; only includes open access empirical/peer-reviewed research; science and social science focused

ChatGPT: refines a research question, determines subject terms, and suggests related terms; not suitable for finding actual publications
Citation tracing for literature reviews

Connected Papers: only includes articles

Research Rabbit: only includes articles; sources mostly from academic journals

Ideation & Keywords ChatGPT: create prompts for subtopics, organize/outline a paper, and brainstorm open data sources; request keywords and boolean search strings related to a specific research question; not suitable for producing citations; all content input into ChatGPT becomes useable by OpenAI

ChatPDF: only a paragraph or two is referred to for the answer

Consensus: provides study snapshots with population, sample size, methods, and outcomes; synthesize feature provides summary of all results and offers consensus graph

Need More Help?

Ethical Considerations

Lack of transparency and bias with datasets

Large language models (LLMs) are trained on a wide variety of datasets and aren't always transparent on which datasets are included and excluded. As a researcher, it is important to continuously critique the quality of generated content for bias and inclusivity. 

Fake citations

GenAI can combine results from its existing datasets into citations that don't actually exist. This is called a hallucination. As a researcher, check generated citations to ensure credibility and correctness before sharing or using.  


Using information generated from LLMs without stating so is plagiarizing. Since LLMs aren't always transparent, researchers must be careful not to take someone else's work without providing proper credit and acknowledgment. 


Information you input into generative AI tools becomes the property of the platform and can be used for LLMs, training, or something else. Never input personally identifiable information or original research ideas into any AI platform.