通过校准价值人设提升跨文化调查模拟
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
AI总结：
本文提出基于价值的人设构建方法，通过校准提升跨文化调查模拟的准确性，减少预测误差，尤其在少数群体中效果显著。
摘要：
大型语言模型（LLMs）越来越多地用于模拟人类意见和调查响应，但其在不同文化中再现人口响应的能力仍有限。现有基于人设的提示方法通常依赖社会人口统计或个性特征，这些只是影响人类响应价值观的间接代理。我们提出一种基于价值的人设构建方法，从调查响应中提取文本描述符，捕捉核心文化维度。通过从目标人群采样价值配置文件，并聚合LLM在不同人设下的响应，我们获得基于观察到的价值分布的群体级预测。我们进一步引入一种校准程序，以提高响应多样性的同时保持估计意见的准确性。我们证明，我们的方法在不同国家减少了预测误差，最大的改进出现在代表性不足的人群中。这大大缩小了与主流LLM先验一致的国家与在训练数据中代表性较低的国家之间的性能差距，同时产生与人类多样性密切匹配的响应分布。
英文摘要：
Large language models (LLMs) are increasingly used to simulate human opinions and survey responses, but their ability to reproduce population responses across cultures remains limited. Existing persona-based prompting methods typically rely on sociodemographic or personality traits, which are only indirect proxies for the values that shape human responses. We propose a value-based persona construction method that derives textual descriptors from survey responses capturing core cultural dimensions. By sampling value profiles from target populations and aggregating LLM responses across personas, we obtain population-level predictions grounded in observed value distributions. We further introduce a calibration procedure that improves response diversity while preserving estimated opinions. We show that our approach reduces prediction error across countries, with the largest improvements observed in underrepresented populations. This substantially narrows the performance gap between countries aligned with dominant LLM priors and those that are less represented in training data, while also yielding response distributions that closely match human diversity.
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。
