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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gendron, Barbara, Guibon, Gaël, D'aquin, Mathieu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918136314331136
author Gendron, Barbara
Guibon, Gaël
D'aquin, Mathieu
author_facet Gendron, Barbara
Guibon, Gaël
D'aquin, Mathieu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts
Gendron, Barbara
Guibon, Gaël
D'aquin, Mathieu
Artificial Intelligence
Computation and Language
Machine Learning
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.
title Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.04926