用价值观构建模拟人物，让AI更准地预测跨文化调查结果。
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
- 基于真实调查数据提取价值观特征，生成更贴近人群的虚拟角色。
- 在多国测试中降低预测误差，尤其提升代表性不足群体的准确性。
- 适合做跨文化研究、市场调研的学者与机构使用。
大型语言模型（LLMs）被广泛用于模拟人类观点和调查回应，但其在跨文化情境下的表现仍受限。现有基于人物设定的提示方法多依赖社会人口或人格特征，这些仅为价值观的间接代理。本文提出一种基于价值观的人物构建方法，从捕捉核心文化维度的调查回应中提取文本描述。通过从目标人群采样价值配置，并聚合多个角色的LLM响应，获得基于实际价值分布的人口级预测。我们进一步引入校准流程，在保持估计观点不变的前提下提升回应多样性。实验表明，该方法显著降低了多国间的预测误差，尤其在代表性不足的人群中改善最明显，大幅缩小了与主流语言模型先验一致国家之间的性能差距，同时生成的回应分布更贴近真实人类多样性。
原文摘要 · Abstract (English)
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.
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。