Publication

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

Conference Article

Conference

International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

Edition

25th

Pages

3301-3303

Doc link

https://doi.org/10.65109/WAZM4282

File

Download the digital copy of the doc pdf document

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.

Categories

artificial intelligence, knowledge engineering.

Scientific reference

A. Olivares-Alarcos, M. Ahsan, S. Sanjaya, H. Lin and G. Alenyà. Blending ontologies and language models to generate sound and natural robot explanations, 25th International Conference on Autonomous Agents and Multiagent Systems, 2026, Paphos, Cyprus, pp. 3301-3303, ACM.