OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling 文章

ArXiv CS.AI2026-05-27NEWSen作者: Adam Bawatneh, Sagar Sapkota, Amrit Singh Bedi, Santu Karmaker, Mubarak Shah

大语言模型

查看原文 →

OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling · 相关技术

相关技术

Large language model iOS LLM ORM ODE language model eval UCT Referring expression comprehension (REC)Query Parts-of-Speech (POS) tags OWL LMM HIS Granular Alignment Paradigm For ENA ARG ANN