English(EN) Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction

新框架揭示LLM难以模拟不一致的人类行为

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

一个名为CoCoEval的新评估框架已被开发出来，用于评估大型语言模型（LLMs）在模拟人类社交互动方面的能力，特别关注不一致和不合作行为。研究人员发现，当前的LLMs，如GPT-4.1、GPT-5.1和Claude Opus 4，表现出此类行为的频率远低于人类，并且提示工程和微调并不能可靠地弥合这一差距。该研究对LLMs作为真实人类社交动态代理的准确性提出了担忧。 AI

影响强调了LLM在准确模拟细微人类社交互动方面的局限性，影响了它们在社会科学研究中的应用。

排序理由介绍LLM新评估框架的研究论文。[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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍LLM新评估框架的研究论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Ryo Kamoi, Ameya Godbole, Binglin Zhou, Xiaoxin Lu, Longqi Yang, Rui Zhang, Mengting Wan, Pei Zhou · 2026-09-11 04:00

评估LLM模拟对话在人类社交互动中建模不一致和不合作行为中的应用

arXiv:2603.17094v2 Announce Type: replace Abstract: Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This paper reconsiders the evaluation of simulated conversations by explicitly recogn…

本文如何被排名

报道来源 [1]

评估LLM模拟对话在人类社交互动中建模不一致和不合作行为中的应用

相关实体

相关话题