English(EN) Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments

研究：大型语言模型在说服判断上与人类一致性有限

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

一项发表在arXiv上的新研究调查了大型语言模型（LLMs）是否会以类似人类的方式响应说服性论点来更新其信念。研究发现，LLMs与人类判断的一致性仅略有体现，Cohen's kappa得分在0.079到0.178之间。虽然人类和LLMs都能识别强烈的说服线索，但人类更容易受到新颖内容和断言性语言的影响，而LLMs则优先考虑主题相似性和格式。研究还指出，与人类相比，LLMs倾向于低估情感诉求并高估可信度信号，而采取第三人称观察视角会增加LLM对说服的抵抗力。 AI

影响强调了在将LLMs用作社会模拟的人类代理时可能存在的风险，并指出了信念更新方面的差异。

排序理由关于LLM行为的学术论文。[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 →

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM行为的学术论文。[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, opinion; 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.CL TIER_1 English(EN) · Lin Chen, Yitong Chen, Yong Li · 2026-09-01 04:00

大型语言模型会像人类一样改变主意吗？诊断单轮说服判断中人类与大型语言模型的差异

arXiv:2608.29803v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations, yet whether they update their beliefs in response to persuasive arguments, as humans do, remains poorly understood. We…

本文如何被排名

报道来源 [1]

大型语言模型会像人类一样改变主意吗？诊断单轮说服判断中人类与大型语言模型的差异

相关实体

相关话题