Slika na naslovnici

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

Shranjeno v:
izdano v:Journal of the Medical Library Association vol. 113, no. 1 (Jan 2025), p. 92
Glavni avtor: Portillo, Ivan
Drugi avtorji: Carson, David
Izdano:
University Library System, University of Pittsburgh
Teme:
Library of Congress Chapman University
Language
User services
Pharmacy
E-books
Integrated library systems-ILS
Medical libraries
Library collections
Researchers
Librarians
Physical therapy
Library cataloging
Health sciences
Hallucinations
Collection development
Large language models
Generative artificial intelligence
Chatbots
Physician assistants
Library associations
Information retrieval
Collection analysis
Information professionals
Libraries
Collection
Health
Science
Artificial intelligence
Language modeling
Online dostop:Citation/Abstract
Full Text
Full Text - PDF
Oznake: Označite
Brez oznak, prvi označite!
Resumen:This project investigated the potential of generative Al models in aiding health sciences librarians with collection development. Researchers at Chapman University's Harry and Diane Rinker Health Science campus evaluated four generative Al 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.
ISSN:1536-5050
1558-9439
0025-7338
DOI:10.5195/jmla.2025.2079
Fuente:Healthcare Administration Database