Generative AI Meets Cataloging Practice
Findings from a Comparative Pilot Study
DOI:
https://doi.org/10.5860/ital.v45i2.17499Keywords:
Large language models (LLMs), Generative AI, Descriptive Metadata, CatalogingAbstract
This study evaluates the performance of four generative AI models—ChatGPT, DeepSeek, Gemini, and Copilot—in generating descriptive metadata for bibliographic resources. Models were tested on a small, diverse set of resources using four prompt types: a basic prompt, a basic prompt with an example, a detailed prompt referencing Resource Description and Access (RDA) guidelines, and a detailed prompt with an example. Results show that both detailed RDA guidance and the inclusion of sample outputs improved metadata quality, particularly in formatting and field structure. While DeepSeek and ChatGPT showed better performance on the tasks, all models displayed limitations in parsing and following the prompts, using descriptive metadata fields, analyzing subject headings, and assigning URIs. These findings suggest that while generative AI holds potential to assist in metadata creation, its current capabilities fall short of meeting cataloging standards without human review.
References
Brian Dobreski and Christopher Hastings, “AI Chatbots and Subject Cataloging: A Performance Test,” Library Resources & Technical Services 69, no. 2 (2025), https://doi.org/10.5860/lrts.69n2.8440.
Charlene Chou and Tony Chu, “An Analysis of BERT (NLP) for Assisted Subject Indexing for Project Gutenberg,” Cataloging & Classification Quarterly 60, no. 8 (2022): 807–35, https://doi.org/10.1080/01639374.2022.2138666.
Christine DeZelar-Tiedman, “Response to ‘From ChatGPT to CatGPT,’” Information Technology and Libraries 42, no. 4 (2023), https://doi.org/10.5860/ital.v42i4.16991.
David Floyd, “Response to ‘From ChatGPT to CatGPT,’” Information Technology and Libraries 42, no. 4 (2023), https://doi.org/10.5860/ital.v42i4.16995.
Eric H. C. Chow, T. J. Kao, and Xiaoli Li, “An Experiment with the Use of ChatGPT for LCSH Subject Assignment on Electronic Theses and Dissertations,” Cataloging & Classification Quarterly 62, no. 5 (2024): 574–88, https://doi.org/10.1080/01639374.2024.2394516.
Heather Moulaison-Sandy and Zach Coble, “Leveraging AI in Cataloging: What Works, and Why?,” Technical Services Quarterly 41, no. 4 (2024): 375–83, https://doi.org/10.1080/07317131.2024.2394912.
Jenny Bodenhamer, Reliability and Usability of ChatGPT for Library Metadata (Oklahoma State University, 2023), https://hdl.handle.net/20.500.14446/339626.
Koraljka Golub et al., “Automated Dewey Decimal Classification of Swedish Library Metadata Using Annif Software,” Journal of Documentation 80, no. 5 (2024): 1057–79, https://doi.org/10.1108/JD-01-2022-0026.
Koraljka Golub, “Automated Subject Indexing: An Overview,” Cataloging & Classification Quarterly 59, no. 8 (2021): 702–19, https://doi.org/10.1080/01639374.2021.2012311.
Lili Daie, Sungmin Park, Mary Beth Weber, and Alicia Zalusky, “Beta-Testing the Alma AI Metadata Assistant: Early Access Insights from Libraries and Ex Libris,” presented at the ELUNA 2025 Conference, Atlanta, GA, June 20, 2025, https://elunaconf2025.dryfta.com/program-schedule/program/detail/51/beta-testing-the-alma-ai-metadata-assistant-early-access-insights-from-libraries-and-ex-libris.
Osma Suominen, “Annif: DIY Automated Subject Indexing Using Multiple Algorithms,” LIBER Quarterly: The Journal of the Association of European Research Libraries 29, no. 1 (2019): 1–25, https://doi.org/10.18352/lq.10285.
Osma Suominen, Juho Inkinen, and Mona Lehtinen, “Annif and Finto AI: Developing and Implementing Automated Subject Indexing,” Bibliographic Control in the Digital Ecosystem, JLIS.It 13, no. 1 (2022): 265–82, https://doi.org/10.4403/jlis.it-12740.
Richard Brzustowicz, “From ChatGPT to CatGPT: The Implications of Artificial Intelligence on Library Cataloging,” Information Technology and Libraries 42, no. 3 (2023), https://doi.org/10.5860/ital.v42i3.16295.
Shoichi Taniguchi, “Creating and Evaluating MARC 21 Bibliographic Records Using ChatGPT,” Cataloging & Classification Quarterly 62, no. 5 (2024): 527–46, https://doi.org/10.1080/01639374.2024.2394513.
Tess Amram, Robin Goodfellow Malamud, and Cheryl Hollingsworth, “Response to ‘From ChatGPT to CatGPT,’” Information Technology and Libraries 42, no. 4 (2023), https://doi.org/10.5860/ital.v42i4.16983.
Vyacheslav Zavalin and Oksana L. Zavalina, “Are We There Yet? Evaluation of AI-Generated Metadata for Online Information Resources,” Information Research an International Electronic Journal 30 (iConf): 732–40, https://doi.org/10.47989/ir30iConf47215.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Greta Heng, Patricia Lampron, Myung-Ja Han
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors that submit to Information Technology and Libraries agree to the Copyright Notice.
