Blending ontologies and language models to generate sound and natural robot explanations

Abstract

This work introduces an approach to creating semantically grounded and natural robot explanations combining ontology-based reasoning with large language models (LLMs). Ontologies ensure logical consistency and domain grounding, while LLMs provide fluent and interactive explanation generation. Empirical results highlight the potential of ontology–LLM integration to advance explainable robotics, and promote more intuitive human-robot collaboration.