发表机构
Arizona State University; Claremont Graduate University（亚利桑那州立大学; 克莱蒙特研究大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种基于聚合锚点构建合成文化智能体的方法，通过GPS偏好坐标生成配对回应并训练适配器，在保留聚合信号的同时不复制人类回应模式，并提供了分离锚点转移与人类标准一致性的评估框架。
AI 中文摘要
人口提示被广泛用于生成合成调查回应，但它们将推理时提供的信息与预训练期间已编码的关联相结合。我们引入了一种替代构建方法，将声明的聚合偏好锚点映射到按群体索引的选择策略中。对于每个群体，全球偏好调查（GPS）六个坐标的符号确定性地标记一个共享的成对合成回应库，并通过直接偏好优化（DPO）拟合一个参数高效的适配器到这些比较上。我们在候选的世界价值观调查（WVS）项目上评估这些适配器，使用省略国家名称的提示，并区分四个问题：恢复施加的标签、将锚点信号转移到新文本、GPS锚点与人类WVS回应之间的一致性，以及适配器分数与人类分数之间的一致性。适配器恢复了施加的成对标签。在一个有目的选择的十六国发展面板上，适配器的信任分数完全分离了两个GPS符号组，并与连续的GPS信任分数具有0.74的秩相关。在同一面板上，人类-GPS和适配器-人类之间的关联仍未解决，其他偏好维度的结果具有异质性。这些发现表明，锚定策略可以保留声明的聚合信号，而不因此复现人类回应模式。因此，贡献既是一种可检查的构建方法，也是一个将锚点转移与人类标准一致性分离的评估框架。
英文摘要
Population prompts are widely used to generate synthetic survey responses, but they combine information supplied at inference with associations already encoded during pretraining. We introduce an alternative construction that maps declared aggregate preference anchors into group-indexed choice policies. For each population, the signs of six Global Preferences Survey (GPS) coordinates deterministically label a shared bank of paired synthetic responses, and Direct Preference Optimization fits a parameter-efficient adapter to those comparisons. We evaluate the adapters on candidate World Values Survey (WVS) items using prompts that omit country names and distinguish four questions: recovery of the imposed labels, transfer of the anchor signal to new text, coherence between the GPS anchors and human WVS responses, and agreement between adapter and human scores. The adapters recover the imposed pairwise labels. On a purposively selected sixteen-country development panel, adapter trust scores completely separate the two GPS-sign groups and have a rank correlation of (0.74) with continuous GPS trust scores. Human-GPS and adapter-human associations remain unresolved on the same panel, and results for the other preference dimensions are heterogeneous. These findings show that an anchored policy can retain a declared aggregate signal without thereby reproducing human response patterns. The contribution is therefore both an inspectable construction and an evaluation framework that separates anchor transfer from human criterion agreement.
CommentsWorking paper, September 2026. 20 pages
