夸大态度，忽视网络：LLM在模拟虚假信息易感性中的偏见
Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility
AI总结：
研究探讨LLM在模拟虚假信息易感性中的偏见，发现其夸大信念与分享的关联，忽视网络特征，建议LLM模拟更适用于诊断而非替代人类判断。
摘要：
大型语言模型（LLM）在计算社会科学中被用作人类判断的代理，但其再现虚假信息易感性模式的能力尚不明确。我们测试了LLM模拟的调查受访者在接收来自社交调查数据提取的参与者资料时，能否再现人类对虚假信息的信念和分享模式。通过三个在线调查作为基准，评估LLM输出是否匹配观察到的响应分布，并恢复原始调查数据中的特征-结果关联。LLM生成的响应捕捉了广泛的分布趋势，并与人类响应有适度的相关性，但一致夸大了信念与分享之间的关联。拟合到模拟响应的线性模型显示出显著更高的解释方差，并对态度和行为特征赋予不成比例的权重，而相对忽略个人网络特征。对模型生成的推理和LLM训练数据的分析表明，这些扭曲反映了误解相关概念的系统性偏见。我们的发现表明，基于LLM的调查模拟更适合诊断系统性偏离人类判断，而非替代它。
英文摘要：
Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misinformation remains unclear. We test whether LLM-simulated survey respondents, prompted with participant profiles drawn from social survey data measuring network, demographic, attitudinal and behavioral features, can reproduce human patterns of misinformation belief and sharing. Using three online surveys as baselines, we evaluate whether LLM outputs match observed response distributions and recover feature-outcome associations present in the original survey data. LLM-generated responses capture broad distributional tendencies and show modest correlation with human responses, but consistently overstate the association between belief and sharing. Linear models fit to simulated responses exhibit substantially higher explained variance and place disproportionate weight on attitudinal and behavioral features, while largely ignoring personal network characteristics, relative to models fit to human responses. Analyses of model-generated reasoning and LLM training data suggest that these distortions reflect systematic biases in how misinformation-related concepts are represented. Our findings suggest that LLM-based survey simulations are better suited for diagnosing systematic divergences from human judgment than for substituting it.
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。
