Skip to Main Content

Pros and Cons of Using AI for Literature Searching: Home

AI for Literature Searching

CABI states: "When it comes to research, it’s important to remember that AI and A&I are different. They can be used in very different ways for varying purposes. Both are beneficial, but we’re not comparing like with like"

AI tools for literature searching often effectively process text in generating search queries, retrieving relevant references, and summarizing literature.  Nevertheless, the problems of bias and error require users to check AI results carefully. 

This guide explains general pros and cons of using AI Large Language Models (LLMS) for literature searching, as well as specific pros and cons for the tools in the tabs of this page. Each tool was chosen for its ability to search biomedical literature, and the tools' selection was based on easy availability or familiarity to the author of this guide ( Jeanine Williamson Fletcher, University of Tennessee Knoxville Libraries). The latest update for this guide was March 21, 2025. All material in this guide is the personal opinion of the author.

Pros and Cons

Pros

  • Has language processing abilities due to models that predict text
  • Does not require users to put in all possible keywords or use Boolean logic (AND and OR operators)
  • Can summarize literature in some instances
  • Can explain why a reference is relevant, or not, in some tools
  • In some cases can export results to citation managers

Cons

  • Only as good as the information it searches
  • Serious risk for hallucinations and other errors that is disguised by scholarly tone of results
  • Some full-text hidden behind paywalls
  • Some references incorrectly exported to citation managers
  • "Black Box" (untransparent) algorithms make reproducibility difficult.

Related Publications

Bolaños, F., Salatino, A., Osborne, F., & Motta, E. (2024). Artificial intelligence for literature reviews: opportunities and challenges. Artificial Intelligence Review, 57(10). https://doi.org/10.1007/s10462-024-10902-3 

Enomoto, M., Tseng, C. H., Hsu, Y. C., Thuy, L. T. T., & Nguyen, M. H. (2023). Collaborating with AI in literature search-An important frontier. Hepatol Commun, 7(12). https://doi.org/10.1097/HC9.0000000000000336 

Gusenbauer, M. (2023). Audit AI search tools now, before they skew research. Nature, 617, 439. 

Kiester, L., & Turp, C. (2022). Artificial intelligence behind the scenes: PubMed's Best Match algorithm. J Med Libr Assoc, 110(1), 15-22. https://doi.org/10.5195/jmla.2022.1236 

Mozelius, P., & Humble, N. (2024). On the Use of Generative AI for Literature Reviews: An Exploration of Tools and Techniques. European Conference on Research Methodology for Business and Management Studies, ECRM 2024, 

Tomczyk, P., Brüggemann, P., Mergner, N., & Petrescu, M. (2024). Are AI tools better than traditional tools in literature searching? Evidence from E-commerce research. Journal of Librarianship and Information Science, 1-11. https://doi.org/10.1177/09610006241295802

Williamson, J. M., & Fernandez, P. (2025). “Through the looking glass: envisioning new library technologies” academic search using artificial intelligence tools. Library Hi Tech News, 42(2), 1-5. https://doi.org/10.1108/LHTN-01-2025-0014 

Information sources most used by AIs