20 January 2026

Our group has presented a new paper at the Theory of Mind for Artificial Intelligence Workshop at the 40th conference of the Association for Artificial Intelligence (AAAI 2026) in Singapore.

In our paper “Theory of Mind for Explainable Human-Robot Interaction”, we explore a new perspective on theory of mind (ToM) in the field of human-robot interaction (HRI) by approaching it from the perspective of explainable artificial intelligence (XAI). We highlight evidence showing that XAI and ToM in HRI pursue related goals, and therefore propose considering ToM as a form of XAI. This paper evaluates ToM using an XAI evaluation framework and identifies a critical gap in the application of ToM within HRI, as existing methods rarely assess the extent to which explanations correspond to the robot’s actual internal reasoning. To address this limitation, we propose integrating ToM into XAI evaluation frameworks. By embedding ToM principles inside XAI, we advocate for a shift in perspective, prioritizing informational needs and the user’s point of view.

You can reach the full paper here.