Ontology Semantic Disambiguation by LLM

Anastasiia Riabova, Rémy Kessler, Nicolas Béchet

2025

Abstract

Within the BPP project, a combination of statistics and word n-gram extraction enabled the creation of a bilingual (French/English) ontology in the field of e-recruitment. The produced dataset was of good quality, but it still contained errors. In this paper, we present an approach that explores the use of large language models (LLMs) to automate the validation and enrichment of ontologies and knowledge graphs. Starting with a naive prompt and using small language models (SLMs), we tested various approaches, including zero-shot, few-shot, chain-of-thought (CoT) reasoning, and self-consistency (SC) decoding. The preliminary results are encouraging, demonstrating the ability of LLMs to make complex distinctions and to evaluate the relationships derived from our ontology finely.

Paper Citation

in Harvard Style

Riabova A., Kessler R. and Béchet N. (2025). Ontology Semantic Disambiguation by LLM. In Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD; ISBN 978-989-758-769-6, SciTePress, pages 175-183. DOI: 10.5220/0013834800004000

in Bibtex Style

@conference{keod25,
author={Anastasiia Riabova and Rémy Kessler and Nicolas Béchet},
title={Ontology Semantic Disambiguation by LLM},
booktitle={Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD},
year={2025},
pages={175-183},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013834800004000},
isbn={978-989-758-769-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD
TI - Ontology Semantic Disambiguation by LLM
SN - 978-989-758-769-6
AU - Riabova A.
AU - Kessler R.
AU - Béchet N.
PY - 2025
SP - 175
EP - 183
DO - 10.5220/0013834800004000
PB - SciTePress