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.

翻译：大语言模型（LLMs）在计算社会科学中越来越多地被用作人类判断的代理，但其能否再现对错误信息的易感性模式仍不明确。我们测试了LLM模拟的调查受访者（通过输入从社会调查数据中提取的参与者档案进行提示，这些档案测量了网络、人口统计、态度和行为特征）能否再现人类在错误信息相信和分享方面的模式。以三项在线调查为基线，我们评估了LLM输出是否匹配观察到的响应分布，并能否恢复原始调查数据中存在的特征-结果关联。LLM生成的响应捕捉了广泛的分布趋势，并与人类响应显示出适度的相关性，但始终夸大了相信与分享之间的关联。相对于拟合人类响应的模型，拟合模拟响应的线性模型表现出显著更高的解释方差，并且不成比例地重视态度和行为特征，同时很大程度上忽略了个人网络特征。对模型生成推理和LLM训练数据的分析表明，这些扭曲反映了在错误信息相关概念的表征方面存在系统性偏差。我们的研究结果表明，基于LLM的调查模拟更适合用于诊断与人类判断的系统性偏差，而非替代人类判断。