MetaPersona：基于经验社会科学的任务导向合成人群

中文摘要 AI 辅助

用于初始化LLM社会模拟的人物角色面临冷启动问题：现有方法缺乏决定包含哪些属性以及如何分配属性值的原则性基础。因此，合成人群可能错误地表示影响下游行为的人口构成、潜在属性和依赖结构。我们引入了MetaPersona-DB，这是一个包含11,000多项实证人类受试者研究的数据集，标注了任务相关变量、报告的关系和总体人口统计。基于这一资源，我们提出了MetaPersona框架，该框架检索任务相关证据，构建源自文献的人物角色依赖图，并从连接人口统计、潜在属性和结果的经验先验中采样合成人群。在三个下游案例研究、三个基线和三个前沿模型中，结果因任务和模型而异：MetaPersona在错误信息信念和AI工具情感方面表现强劲，而在收入再分配方面的结果则喜忧参半。它还使用GPT-5.2将人物角色构建成本降低到每任务低于0.5美元。最后，我们展示了MetaPersona-Studio，一个用于经验基础人物角色生成的原型交互界面。

英文摘要

Personas used to seed LLM social simulations face a cold-start problem: existing methods lack a principled basis for deciding which attributes to include and how to assign their values. As a result, synthetic populations may misrepresent the demographic composition, latent attributes, and dependency structure that shape downstream behavior. We introduce MetaPersona-DB, a dataset of 11,000+ empirical human-subjects studies annotated with task-relevant variables, reported relationships, and aggregate-level population statistics. Building on this resource, we propose MetaPersona, a framework that retrieves task-relevant evidence, constructs literature-derived persona dependency graphs, and samples synthetic populations from empirical priors linking demographics, latent attributes, and outcomes. Across three downstream case studies, three baselines, and three frontier models, results vary by task and model: MetaPersona performs strongly on misinformation belief and AI-tool sentiment, while results on income redistribution are mixed. It also reduces persona-construction cost to under $0.5 per task using GPT-5.2. Finally, we present MetaPersona-Studio, a prototype interactive interface for empirically grounded persona generation.

发表机构

• University of Southern California（南加州大学）
• University of California, Irvine（加州大学尔湾分校）
• Arizona State University（亚利桑那州立大学）

机构由 AI 辅助整理，请以论文原文为准。