University of North Texas (University of North Texas, College of Information)

The University of North Texas Department of Information Science and University Libraries will investigate the applicability of locally run large language models (LLMs) to assist the subject cataloging of digital and print library resources. The research team will address both how LLM-based models can be developed to generate accurate cataloging results, as well as how they can be integrated into cataloging procedures to assist library staff. The project team will develop, analyze, and share methodologies and code for the LLM-based models, input and output data, survey instruments, and reports. The work will build knowledge for the future development and deployment of LLM-based applications for cataloging, furthering innovative approaches to digital collection management across institutions and thereby improving discovery and ensuring the accessibility of these resources for a broad, nationwide audience of potential users.