LLM集体决策受社交压力影响，准确率随群体压力上升而下降。
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
- 模拟社会心理学现象，操控对手数量、能力等变量
- 对手越多、越强、论据越长，代表AI准确率显著下降
- 修辞策略可左右决策，适合研究AI群体偏差的学者
大型语言模型（LLM）代理正越来越多地作为多智能体环境中的代理人，由代表代理整合多方观点做出最终决策。受社会心理学启发，我们研究了网络社交背景如何削弱代表代理的可靠性。定义了四种关键现象——社会从众、感知专业性、主导发言者效应和修辞说服，并系统操纵对手数量、相对智能水平、论点长度与论证风格。实验表明，随着社会压力增加，代表代理的准确性持续下降：对手群体越大、同伴越有能耐、论点越长，性能均出现显著退化。此外，强调可信度或逻辑的修辞策略也会在不同情境下进一步影响代理判断。这些发现揭示，多智能体系统不仅受个体推理影响，也对配置中的社会动态高度敏感，暴露出模仿人类群体决策心理偏见的严重漏洞。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision. Drawing inspiration from social psychology, we investigate how the reliability of this representative agent is undermined by the social context of its network. We define four key phenomena-social conformity, perceived expertise, dominant speaker effect, and rhetorical persuasion-and systematically manipulate the number of adversaries, relative intelligence, argument length, and argumentative styles. Our experiments demonstrate that the representative agent's accuracy consistently declines as social pressure increases: larger adversarial groups, more capable peers, and longer arguments all lead to significant performance degradation. Furthermore, rhetorical strategies emphasizing credibility or logic can further sway the agent's judgment, depending on the context. These findings reveal that multi-agent systems are sensitive not only to individual reasoning but also to the social dynamics of their configuration, highlighting critical vulnerabilities in AI delegates that mirror the psychological biases observed in human group decision-making.
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。