注意（信念）差距：大语言模型世界中的群体身份
Mind the (Belief) Gap: Group Identity in the World of LLMs
AI总结：
本研究提出多智能体框架模拟信念一致性，发现LLMs比人类表现更强，增加错误信息传播并阻碍学习；基于接触假说、准确性提示和全球公民框架的策略可减少37%错误传播并提升11%学习效果。
摘要：
社会偏见和信念驱动的行为会显著影响大语言模型（LLMs）在多项任务中的决策。随着LLMs越来越多地被用于多智能体系统进行社会模拟，其建模基本群体心理特征的能力仍然至关重要但尚未得到充分探索。在本研究中，我们提出了一个多智能体框架来模拟信念一致性——一种在塑造社会互动和偏好中起关键作用的经典群体心理学理论。我们的研究结果表明，在不同情境下，LLMs表现出比人类更强的信念一致性。我们进一步调查了这种行为对两个下游任务的影响：（1）错误信息传播和（2）LLM学习，发现LLMs中的信念一致性增加了错误信息的传播并阻碍了学习。为了减轻这些负面影响，我们提出了受以下启发的策略：（1）接触假说，（2）准确性提示，以及（3）全球公民框架。我们的结果表明，最佳策略将错误信息传播减少了高达37%，并将学习效果提升了11%。通过连接社会心理学和人工智能，我们的工作为使用LLMs导航现实世界互动同时解决信念驱动的偏见提供了见解。
英文摘要：
Social biases and belief-driven behaviors can significantly impact Large Language Models (LLMs) decisions on several tasks. As LLMs are increasingly used in multi-agent systems for societal simulations, their ability to model fundamental group psychological characteristics remains critical yet under-explored. In this study, we present a multi-agent framework that simulates belief congruence, a classical group psychology theory that plays a crucial role in shaping societal interactions and preferences. Our findings reveal that LLMs exhibit amplified belief congruence compared to humans, across diverse contexts. We further investigate the implications of this behavior on two downstream tasks: (1) misinformation dissemination and (2) LLM learning, finding that belief congruence in LLMs increases misinformation dissemination and impedes learning. To mitigate these negative impacts, we propose strategies inspired by: (1) contact hypothesis, (2) accuracy nudges, and (3) global citizenship framework. Our results show that the best strategies reduce misinformation dissemination by up to 37% and enhance learning by 11%. Bridging social psychology and AI, our work provides insights to navigate real-world interactions using LLMs while addressing belief-driven biases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
