Motion2Mind is a curated video benchmark dataset for Theory-of-Mind via nonverbal body language cues that reveals substantial AI performance gaps versus humans in detection and over-interpretation in explanations.
arXiv preprint arXiv:2401.08743 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
PDDL-Mind improves LLM accuracy on theory-of-mind benchmarks by over 5% by translating stories into verifiable PDDL states that decouple environment tracking from belief inference.
citing papers explorer
-
Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language
Motion2Mind is a curated video benchmark dataset for Theory-of-Mind via nonverbal body language cues that reveals substantial AI performance gaps versus humans in detection and over-interpretation in explanations.
-
Reinforcing Human Behavior Simulation via Verbal Feedback
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
-
PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking
PDDL-Mind improves LLM accuracy on theory-of-mind benchmarks by over 5% by translating stories into verifiable PDDL states that decouple environment tracking from belief inference.