Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts
This work addresses the problem of ensuring predictable and user-personalized responses in conversational AI, though it is incremental as it builds on existing ontology and fine-tuning methods.
The authors tackled the challenge of controlling Large Language Models in conversations by proposing an ontology-based approach to formally define qualitative conversational features, such as language proficiency levels, and applied it to improve transparency and consistency in LLM responses.
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.