2000 character limit reached
A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks (2502.06470v1)
Published 10 Feb 2025 in cs.CL and cs.AI
Abstract: Theory of Mind (ToM), the ability to attribute mental states to others and predict their behaviour, is fundamental to social intelligence. In this paper, we survey studies evaluating behavioural and representational ToM in LLMs, identify important safety risks from advanced LLM ToM capabilities, and suggest several research directions for effective evaluation and mitigation of these risks.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.