Today at ICSR25 - 17th International Conference on Social Robotics, I presented the paper "RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors" by Agnese Augello, Edoardo Datteri, Antonio Lieto, Maria Rausa and Nicola Zagni
#ICSR2025
Title: RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors
Abstract:
In this work we present and test a RAG-based model called RAGGAE (i.e. RAG for the General Analysis of Explanans) tested in the context of Human Explanation of Robotic BehaviorS (HERBS).
The RAGGAE model makes use of an ontology of explanations, enriching the knowledge of state of the art general purpose Large Language Models like Google Gemini 2.0 Flash, DeepSeek R1 and GPT-4o. The results show that the combination of a general LLM with a symbolic, and philosophically grounded, ontology can be a useful instrument to improve the investigation, identification and the analysis of the types of explanations that humans use to verbalize - and make sense of - the behavior of robotic agents.
Paper: https://www.ciitlab.org/RAGGAE4HERBS_ICSR2025.pdf
System Live: https://www.ciitlab.org/agent.html
Index Terms: #artificialintelligence #HumanRobotInteraction #explanation #largelanguaagemodels #rag #socialrobotics #robots #humanexplanation #cognitivesystems #LLM
@academicchatter @cognition