Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries
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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University Library System, University of Pittsburgh
2025-01-01
|
| Series: | Journal of the Medical Library Association |
| Subjects: | |
| Online Access: | http://jmla.pitt.edu/ojs/jmla/article/view/2079 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536202735353856 |
|---|---|
| author | Ivan Portillo David Carson |
| author_facet | Ivan Portillo David Carson |
| author_sort | Ivan Portillo |
| collection | DOAJ |
| description | 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.
|
| format | Article |
| id | doaj-art-b7b9fe430fda43b6a36c035cc1a28d79 |
| institution | Kabale University |
| issn | 1536-5050 1558-9439 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | University Library System, University of Pittsburgh |
| record_format | Article |
| series | Journal of the Medical Library Association |
| spelling | doaj-art-b7b9fe430fda43b6a36c035cc1a28d792025-01-14T23:39:28ZengUniversity Library System, University of PittsburghJournal of the Medical Library Association1536-50501558-94392025-01-01113110.5195/jmla.2025.2079Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences librariesIvan Portillo0David Carson1Chapman UniversityChapman UniversityThis 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. http://jmla.pitt.edu/ojs/jmla/article/view/2079Generative Artificial IntelligenceLarge Language ModelsChatGPTMicrosoft CopilotPerplexityGoogle Gemini |
| spellingShingle | Ivan Portillo David Carson Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries Journal of the Medical Library Association Generative Artificial Intelligence Large Language Models ChatGPT Microsoft Copilot Perplexity Google Gemini |
| title | Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries |
| title_full | Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries |
| title_fullStr | Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries |
| title_full_unstemmed | Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries |
| title_short | Making the most of Artificial Intelligence and Large Language Models to support collection development in health sciences libraries |
| title_sort | making the most of artificial intelligence and large language models to support collection development in health sciences libraries |
| topic | Generative Artificial Intelligence Large Language Models ChatGPT Microsoft Copilot Perplexity Google Gemini |
| url | http://jmla.pitt.edu/ojs/jmla/article/view/2079 |
| work_keys_str_mv | AT ivanportillo makingthemostofartificialintelligenceandlargelanguagemodelstosupportcollectiondevelopmentinhealthscienceslibraries AT davidcarson makingthemostofartificialintelligenceandlargelanguagemodelstosupportcollectiondevelopmentinhealthscienceslibraries |