Entity Quality Enhancement in Knowledge Graphs through LLM-based Question Answering

Morteza Kamaladdini Ezzabady, Farah Benamara


Abstract
Most models for triple extraction from texts primarily focus on named entities. However, real-world applications often comprise non-named entities that pose serious challenges for entity linking and disambiguation. We focus on these entities and propose the first LLM-based entity revision framework to improve the quality of extracted triples via a multi-choice question-answering mechanism. When evaluated on two benchmark datasets, our results show a significant improvement, thereby generating more reliable triples for knowledge graphs.
Anthology ID:
2025.genaik-1.14
Volume:
Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Genet Asefa Gesese, Harald Sack, Heiko Paulheim, Albert Merono-Penuela, Lihu Chen
Venues:
GenAIK | WS
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
136–145
Language:
URL:
https://aclanthology.org/2025.genaik-1.14/
DOI:
Bibkey:
Cite (ACL):
Morteza Kamaladdini Ezzabady and Farah Benamara. 2025. Entity Quality Enhancement in Knowledge Graphs through LLM-based Question Answering. In Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK), pages 136–145, Abu Dhabi, UAE. International Committee on Computational Linguistics.
Cite (Informal):
Entity Quality Enhancement in Knowledge Graphs through LLM-based Question Answering (Kamaladdini Ezzabady & Benamara, GenAIK 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaik-1.14.pdf