Theory of Mind in Human-AI Interaction

Abstract

Theory of Mind (ToM) refers to humans’ capability of attributing mental states such as goals, emotions, and beliefs to ourselves and others. This concept has become of great interest in human-AI interaction research. Given the fundamental role of ToM in human social interactions, many researchers have been working on methods and techniques to equip AI with an equivalent of human ToM capability to build highly socially intelligent AI. Another line of research on ToM in human-AI interaction aims at providing human-centered AI design implications through exploring people’s tendency to attribute mental states such as blame, emotions, and intentions to AI, along with the role that AI should play in the interaction (e.g., as a tool, partner, teacher, and more) to align with people’s expectations and mental models. Together, these two research perspectives on ToM form an emerging paradigm of “Mutual Theory of Mind (MToM)” in human-AI interaction, where both the human and the AI each possess some level of ToM-like capability during interactions. The goal of this workshop is to bring together researchers working on different perspectives of ToM in human-AI interaction to define a unifying research agenda on the human-centered design and development of Mutual Theory of Mind (MToM) in human-AI interaction. We aim to explore three broad topics to inspire workshop discussions: - Designing and building AI’s ToM-like capability - Understanding and shaping human’s ToM in human-AI interaction - Envisioning MToM in human-AI interaction