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

Barbara Gendron, Gael Guibon, Mathieu d’Aquin


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.
Anthology ID:
2026.kallm-1.3
Volume:
Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Gilles Sérasset, Katerina Gkirtzou, Michael Cochez, Jan-Christoph Kalo
Venues:
KaLLM | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
20–35
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-kgllm-03
DOI:
10.63317/446x4ysrhfeq
Bibkey:
Cite (ACL):
Barbara Gendron, Gael Guibon, and Mathieu d’Aquin. 2026. Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 20–35, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation (Gendron et al., KaLLM 2026)
Copy Citation: