EUVIMEDEUVIMED entdecken
Crossref

A Hybrid Framework for Subject Analysis: Integrating Embedding‐Based Regression Models with Large Language Models

Jinyu Liu, Xiaoying Song, Diana Zhang, Jason Thomale, Daqing He, Lingzi Hong

Proceedings of the Association for Information Science and Technology · 2025-10 · 62 (1) · 445-457

DOI: 10.1002/pra2.1269 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Association for Information Science and Technology, online erschienen am 16.10.2025. Verfasst von Jinyu Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification and summarization tasks, but their capability to perform subject analysis is underexplored. Multi‐label classification with traditional machine learning (ML) models has been used for subject analysis but struggles with unseen cases. LLMs offer an alternative but often over‐generate and hallucinate. Therefore, we propose a hybrid framework that integrates embedding‐based ML models with LLMs. This approach uses ML models to (1) predict the optimal number of LCSH labels to guide LLM predictions and (2) post‐edit the predicted terms with actual LCSH terms to mitigate hallucinations. We experimented with LLMs and the hybrid framework to predict the subject terms of books using the Library of Congress Subject Headings (LCSH). Experiment results show that providing initial predictions to guide LLM generations and imposing post‐edits result in more controlled and vocabulary‐aligned outputs.

Zitieren

APA

Liu, J., Song, X., Zhang, D., Thomale, J., He, D., & Hong, L. (2025). A Hybrid Framework for Subject Analysis: Integrating Embedding‐Based Regression Models with Large Language Models. Proceedings of the Association for Information Science and Technology, 62(1), 445-457. https://doi.org/10.1002/pra2.1269

Vancouver

Liu J, Song X, Zhang D, Thomale J, He D, Hong L. A Hybrid Framework for Subject Analysis: Integrating Embedding‐Based Regression Models with Large Language Models. Proceedings of the Association for Information Science and Technology. 2025;62(1):445-457. doi:10.1002/pra2.1269

BibTeX
@article{Liu2025,
  author = {Liu, Jinyu and Song, Xiaoying and Zhang, Diana and Thomale, Jason and He, Daqing and Hong, Lingzi},
  title = {A Hybrid Framework for Subject Analysis: Integrating Embedding‐Based Regression Models with Large Language Models},
  journal = {Proceedings of the Association for Information Science and Technology},
  year = {2025},
  volume = {62},
  number = {1},
  pages = {445--457},
  doi = {10.1002/pra2.1269}
}
Kostenlos starten →