LLM在辩论中出现意见漂移，少数群体易被边缘化。
Network Effects and Agreement Drift in LLM Debates
- 构建可控同质性与群体规模的网络模型模拟多轮辩论
- 发现代理倾向于向特定立场偏移，形成意见漂移
- 提醒警惕结构效应与模型偏差混淆，慎用LLM模拟人类社会
大型语言模型（LLMs）展现出前所未有的类人社交行为模拟能力，可用于复杂社会系统的仿真。然而，在涉及少数群体的高度失衡情境下，这些模拟的可信度仍不明确。本文通过控制同质性与群体规模的网络生成模型，研究了LLM代理在多轮辩论中的集体行为。结果揭示了一种定向倾向，称为“意见漂移”（agreement drift），即代理更倾向于向意见尺度上的特定位置靠拢。整体发现表明，在将LLM群体视为人类群体的行为代理前，必须区分结构性效应与模型偏差的影响。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated an unprecedented ability to simulate human-like social behaviors, making them useful tools for simulating complex social systems. However, it remains unclear to what extent these simulations can be trusted to accurately capture key social mechanisms, particularly in highly unbalanced contexts involving minority groups. This paper uses a network generation model with controlled homophily and class sizes to examine how LLM agents behave collectively in multi-round debates. Moreover, our findings highlight a particular directional susceptibility that we term \textit{agreement drift}, in which agents are more likely to shift toward specific positions on the opinion scale. Overall, our findings highlight the need to disentangle structural effects from model biases before treating LLM populations as behavioral proxies for human groups.
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。