PulseAugur
实时 07:16:39
English(EN) Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf

大型语言模型在社交推理游戏中难以平衡信任与指控

研究人员开发了一个新的基准,用于评估大型语言模型(LLMs)在“狼人杀”等社交推理游戏中的表现,重点关注它们的信念如何根据指控而转变。研究发现,虽然较大的LLMs能更好地区分狼人和村民,但它们仍然深受指控的影响,特别是当指控来自可信来源时,即使该来源是狼人。研究结果表明,当前开放权重LLMs在战略沟通中难以平衡来源信任与指控内容。 AI

影响 这项研究突显了LLM推理和信任评估方面的局限性,指出了在处理细微的社交互动和信息整合能力方面的改进方向。

排序理由 学术论文,详细介绍了一个用于LLM评估的新基准。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

大型语言模型在社交推理游戏中难以平衡信任与指控

本文如何被排名

Signal score
23 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了一个用于LLM评估的新基准。[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]

  1. arXiv cs.CL TIER_1 English(EN) · Yu-Yu Yang, Ti-Rong Wu, Hung Guei, Hsing-Yu Chen, I-Chen Wu ·

    大型语言模型信任指控者还是指控本身?衡量狼人游戏中的信念转变

    arXiv:2609.12446v1 Announce Type: cross Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evaluation benchmark in Werewolf for analyzing communicati…