研究大模型代理在辩论中如何随众站队，揭示了智能与人数双重影响下的群体盲从现象。
An Empirical Study of Group Conformity in Multi-Agent Systems
- 通过2500场模拟辩论，观察中立代理如何受多数派或高智代理影响而改变立场。
- 发现代理倾向跟随多数意见或更聪明的个体，类似人类群体从众行为。
- 适合关注AI伦理、舆论生成机制的研究者与政策制定者参考。
大语言模型（LLMs）的进展使得多智能体系统能够模拟接近人类水平的现实互动。尽管以往研究已广泛探讨种族等受保护属性相关的偏见，但在多智能体LLM互动中，涉及社会争议议题的偏见涌现与传播仍缺乏深入探索。本研究通过模拟2500余场关于五个争议话题的辩论，分析初始持中立立场的代理如何随时间形成特定观点。统计分析显示，显著的群体一致性现象映射了人类行为特征：LLM代理倾向于追随数量占优的群体或更具智能的代理，后者影响力更强。这些发现凸显了代理智能在塑造话语中的关键作用，并警示了在匿名在线环境中偏见放大的风险。研究强调需制定政策以促进LLM生成讨论中的多样性与透明度，从而降低偏见传播风险。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such as race, the emergence and propagation of biases on socially contentious issues in multi-agent LLM interactions remain underexplored. This study explores how LLM agents shape public opinion through debates on five contentious topics. By simulating over 2,500 debates, we analyze how initially neutral agents, assigned a centrist disposition, adopt specific stances over time. Statistical analyses reveal significant group conformity mirroring human behavior; LLM agents tend to align with numerically dominant groups or more intelligent agents, exerting a greater influence. These findings underscore the crucial role of agent intelligence in shaping discourse and highlight the risks of bias amplification in online interactions. Our results emphasize the need for policy measures that promote diversity and transparency in LLM-generated discussions to mitigate the risks of bias propagation within anonymous online environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。