Loading...
Leveraging Generative AI for the Creation of Valid MARC21 Bibliographic Records from Unstructured Data
Husić, Geoff
Husić, Geoff
Citations
Altmetric:
Abstract
Using ChatGPT 4o and O3, in this case, for cataloging materials in Slavic languages highlights its strengths and areas requiring careful handling. These languages, characterized by diverse diacritical marks, alphabetic, and script variants, present significant challenges in character encoding and romanization. Through targeted prompts referencing these guidelines, ChatGPT demonstrates enhanced precision and compliance, streamlining the cataloging of Slavic material, although the application is certainly valid for other broad categories of materials.
Description
Date
2025-06-30
Journal Title
Journal ISSN
Volume Title
Publisher
University of Kansas Libraries
Collections
Research Projects
Organizational Units
Journal Issue
Keywords
Large Language Models (LLMs), MARC21 records, Library cataloging, unstructured bibliographic data, ChatGPT