Skip to main navigation Skip to search Skip to main content

LLM-Powered Entity Alignment for Enhanced Scientific Collaborator Recommendation

Jiaxiao Wang*

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Entity misalignment in knowledge graphs (KGs)—caused by noisy data or inconsistent naming—severely undermines the accuracy of academic collaborator recommendation systems. To address this, we propose a KG-based scholar recommendation system featuring a novel LLM-powered entity alignment method. Our-stage approach first identifies potential matches unsupervisedly, then leverages LLMs' semantic understanding for precise alignment. This high-fidelity alignment directly enhances KG quality, leading to more accurate recommendations. By resolving core entity ambiguity issues, our system aims to significantly improve recommendation reliability. Evaluation on real-world datasets will validate the effectiveness of the alignment method and its impact on recommendation performance. ©ICEB.
Original languageEnglish
Title of host publicationProceedings of The International Conference on Electronic Business, Volume 25
EditorsEldon Y. Li, Ta Van Loi, William Y.C. Wang
Pages279-288
Number of pages10
Publication statusPublished - Aug 2025
Event25th International Conference on Electronic Business (ICEB 2025) - Hanoi, Viet Nam
Duration: 21 Aug 202525 Aug 2025

Publication series

NameProceedings of the International Conference on Electronic Business (ICEB)
Volume25
ISSN (Print)1683-0040

Conference

Conference25th International Conference on Electronic Business (ICEB 2025)
PlaceViet Nam
CityHanoi
Period21/08/2525/08/25

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

  • collaboration recommendation
  • entity alignment
  • Knowledge graphs
  • large language models
  • recommendation systems

Fingerprint

Dive into the research topics of 'LLM-Powered Entity Alignment for Enhanced Scientific Collaborator Recommendation'. Together they form a unique fingerprint.

Cite this