Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation
This work addresses the need for more predictable and personalized conversational AI, offering a modular and interpretable solution that can be extended to new domains, though it is incremental in building on existing controlled generation methods.
The authors tackled the problem of unpredictable and non-personalized outputs from conversational LLMs by proposing a lightweight, ontology-driven framework for controlled generation, which consistently outperformed pre-trained baselines across seven models on tasks like English proficiency and content polarity.
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.