Pré-Publication, Document De Travail Année : 2025

Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts

Résumé

The controllability of Large Language Models (LLMs) when used as conversational agents is a key challenge, particularly to ensure predictable and user-personalized responses. This work proposes an ontology-based approach to formally define conversational features that are typically qualitative in nature. By leveraging a set of linguistic descriptors, we derive quantitative definitions for qualitatively-defined concepts, enabling their integration into an ontology for reasoning and consistency checking. We apply this framework to the task of proficiency-level control in conversations, using CEFR language proficiency levels as a case study. These definitions are then formalized in description logic and incorporated into an ontology, which guides controlled text generation of an LLM through fine-tuning. Experimental results demonstrate that our approach provides consistent and explainable proficiency-level definitions, improving transparency in conversational AI.

Fichier principal
Vignette du fichier
TOTH_extended_abstract.pdf (2.8 Mo) Télécharger le fichier

Dates et versions

hal-05240495 , version 1 (04-09-2025)

Licence

Identifiants

  • HAL Id : hal-05240495 , version 1

Citer

Barbara Gendron, Gaël Guibon, Mathieu D’aquin. Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts. 2025. ⟨hal-05240495⟩
253 Consultations
174 Téléchargements

Partager

  • More