English(EN) MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

新基准MuSeToM测试LLM在心智理论中的信念修正能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

研究人员推出了MuSeToM，这是一个旨在评估大型语言模型（LLM）在心智理论（ToM）背景下的信念修正能力的新基准。该基准包含2,415个实例，源自BigToM和OpenToM，评估LLM是否能确定何时感知证据需要信念的改变，并推断更新后的信念状态。使用MuSeToM的评估显示，当前最先进的LLM通常能检测到潜在的信念变化，但在准确识别修正后的信念方面存在困难，有时会过分强调感知上突出但认知上较弱的线索。 AI

影响该基准有望推动LLM在社会推理和基于证据理解细微信念更新方面的能力改进。

排序理由该集群描述了一篇介绍用于评估LLM能力的新型基准的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍用于评估LLM能力的新型基准的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Chunkit Chan, Kawai Chung, Sze Heng Douglas Kwok, Yuxuan Liu, Yauwai Yim, Tianshi Zheng, Haochen Shi, Qing Zong, Wong Kai Chung, Pak Hin Lau, Calvin Yang, Yifan Gao, Xiaoman Pan, Ginny Wong, Simon See, Yangqiu Song · 2026-11-14 05:00

MuSeToM：跨越六种感官的文本线索信念修正的多感官评估

arXiv:2611.16662v1 Announce Type: cross Abstract: Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in large language models (LLMs) mainly focus on static belief attribution and false-belief reas…

本文如何被排名

报道来源 [1]

MuSeToM：跨越六种感官的文本线索信念修正的多感官评估

相关实体

相关话题