LLM在群体心理模拟中表现更强信念一致性，易传播假信息并阻碍学习。
Mind the (Belief) Gap: Group Identity in the World of LLMs
- 构建多智能体框架模拟信念一致性心理机制
- 信念一致性使假信息传播增37%，学习效率降11%
- 提出接触假说等策略，有效缓解偏差
社会偏见与信念驱动行为会显著影响大型语言模型在多项任务中的决策。随着大模型越来越多地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至关重要但尚未充分探索。本研究提出一种多智能体框架，模拟信念一致性这一经典群体心理学理论，该理论在塑造社会互动和偏好中起关键作用。研究发现，大模型在多种情境下表现出比人类更强烈的信念一致性。我们进一步探讨了这种行为对两个下游任务的影响：(1) 假信息传播和(2) 大模型学习，结果表明，大模型的信念一致性加剧了假信息传播并阻碍了学习。为缓解这些负面影响，我们提出了受接触假说、准确提醒和全球公民框架启发的策略。实验显示，最优策略可将假信息传播减少高达37%，并将学习效果提升11%。本工作连接社会心理学与人工智能，为利用大模型模拟真实世界互动并应对信念驱动偏见提供洞见。
原文摘要 · Abstract (English)
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.
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。