Service restrictions from February 12-22, 2026—more information on the University Library website

Result: Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries.

Title:
Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries.
Authors:
Portillo I; iportillo@chapman.edu, Health Sciences Librarian, Director of Rinker Campus Library Services, Leatherby Libraries, Chapman University, Irvine, CA., Carson D; carsondav@ohsu.edu, Health Sciences Education & Research Librarian, Oregon Health & Science University, Portland, OR.
Source:
Journal of the Medical Library Association : JMLA [J Med Libr Assoc] 2025 Jan 14; Vol. 113 (1), pp. 92-93.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Medical Library Association Country of Publication: United States NLM ID: 101132728 Publication Model: Print Cited Medium: Internet ISSN: 1558-9439 (Electronic) Linking ISSN: 15365050 NLM ISO Abbreviation: J Med Libr Assoc Subsets: MEDLINE
Imprint Name(s):
Original Publication: Chicago, IL : Medical Library Association, c2002-
MeSH Terms:
Artificial Intelligence* , Libraries, Medical*/organization & administration , Library Collection Development*, Humans ; Large Language Models
References:
Brief Bioinform. 2023 Nov 22;25(1):. (PMID: 38168838)
Contributed Indexing:
Keywords: ChatGPT; Generative artificial intelligence; Google Gemini; Microsoft Copilot; Perplexity; collection assessment; collection development; health sciences libraries; large language models
Entry Date(s):
Date Created: 20250220 Date Completed: 20250508 Latest Revision: 20250522
Update Code:
20250523
PubMed Central ID:
PMC11835035
DOI:
10.5195/jmla.2025.2079
PMID:
39975505
Database:
MEDLINE

Further Information

This project investigated the potential of generative AI models in aiding health sciences librarians with collection development. Researchers at Chapman University's Harry and Diane Rinker Health Science campus evaluated four generative AI models-ChatGPT 4.0, Google Gemini, Perplexity, and Microsoft Copilot-over six months starting in March 2024. Two prompts were used: one to generate recent eBook titles in specific health sciences fields and another to identify subject gaps in the existing collection. The first prompt revealed inconsistencies across models, with Copilot and Perplexity providing sources but also inaccuracies. The second prompt yielded more useful results, with all models offering helpful analysis and accurate Library of Congress call numbers. The findings suggest that Large Language Models (LLMs) are not yet reliable as primary tools for collection development due to inaccuracies and hallucinations. However, they can serve as supplementary tools for analyzing subject coverage and identifying gaps in health sciences collections.
(Copyright © 2025 Ivan Portillo, David Carson.)