Surveys are widely used in social sciences to understand human behavior, but their implementation often involves iterative adjustments that demand significant effort and resources. To this end, researchers have increasingly turned to large language models (LLMs) to simulate human behavior. While existing studies have focused on distributional similarities, individual-level comparisons remain underexplored. Building upon prior work, we investigate whether providing LLMs with respondents' prior information can replicate both statistical distributions and individual decision-making patterns using Partial Least Squares Structural Equation Modeling (PLS-SEM), a well-established causal analysis method. We also introduce the concept of the LLM-Mirror, user personas generated by supplying respondent-specific information to the LLM. By comparing responses generated by the LLM-Mirror with actual individual survey responses, we assess its effectiveness in replicating individual-level outcomes. Our findings show that: (1) PLS-SEM analysis shows LLM-generated responses align with human responses, (2) LLMs, when provided with respondent-specific information, are capable of reproducing individual human responses, and (3) LLM-Mirror responses closely follow human responses at the individual level. These findings highlight the potential of LLMs as a complementary tool for pre-testing surveys and optimizing research design.

翻译：调查在社会科学中被广泛用于理解人类行为，但其实施通常涉及迭代调整，需要耗费大量精力和资源。为此，研究者们越来越多地转向使用大型语言模型（LLMs）来模拟人类行为。尽管现有研究主要关注分布层面的相似性，但个体层面的比较仍有待深入探索。基于先前工作，我们研究了向LLMs提供受访者先验信息是否能够同时复现统计分布和个体决策模式，并采用偏最小二乘结构方程模型（PLS-SEM）这一成熟的因果分析方法进行验证。我们还引入了LLM-Mirror的概念，即通过向LLM提供受访者特定信息而生成的用户角色。通过比较LLM-Mirror生成的回答与实际个体调查回答，我们评估了其在复现个体层面结果方面的有效性。我们的研究结果表明：（1）PLS-SEM分析显示LLM生成的回答与人类回答具有一致性；（2）当提供受访者特定信息时，LLMs能够复现个体的人类回答；（3）LLM-Mirror的回答在个体层面紧密跟随人类回答。这些发现凸显了LLMs作为调查预测试和研究设计优化的补充工具的潜力。