Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation

TL;DR

This paper introduces a lightweight, ontology-based control framework for large language models to improve conversational predictability and personalization through constrained, explainable content generation.

Contribution

It presents a novel end-to-end method for modular, ontology-driven control of LLM outputs, validated on conversational tasks with improved performance and interpretability.

Findings

Outperforms pre-trained baselines on conversational tasks

Effective on smaller models, maintaining model-agnosticism

Enhances alignment with strategy instructions

Abstract

Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight, and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.