Communication Dans Un Congrès Année : 2025

Ontology Semantic Disambiguation by LLM

Résumé

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

Fichier principal
Vignette du fichier
138348.pdf (215.91 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05446587 , version 1 (15-01-2026)

Licence

Identifiants

Citer

Anastasiia Riabova, Rémy Kessler, Nicolas Béchet. Ontology Semantic Disambiguation by LLM. 17th International Conference on Knowledge Engineering and Ontology Development, Oct 2025, Marbella, France. pp.175-183, ⟨10.5220/0013834800004000⟩. ⟨hal-05446587⟩
207 Consultations
119 Téléchargements

Altmetric

Partager

  • More