Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ye, J., Li, Y., Yu, C., Poddar, P., Dey, P., Ye, L., Wang, Z., Hu, X., Ferrara, E., & Zhao, Y. (2026). MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science. https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science
MLA 9
Ye, Jinyi, et al. "MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science." https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science.
Chicago (author–date)
Ye, Jinyi, Yuangang Li, Chenxiao Yu, Preyashi Poddar, Priyanka Dey, Longtian Ye, Zihan Wang, Xiyang Hu, Emilio Ferrara, and Yue Zhao. 2026. "MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science." https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science.
Harvard
Ye, J., Li, Y., Yu, C., Poddar, P., Dey, P., Ye, L., Wang, Z., Hu, X., Ferrara, E. and Zhao, Y. (2026) 'MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science', Available at: https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science.
Vancouver
Ye J, Li Y, Yu C, Poddar P, Dey P, Ye L, et al. MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science. https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science
IEEE
J. Ye, Y. Li, C. Yu, P. Poddar, P. Dey, L. Ye, Z. Wang, X. Hu, E. Ferrara, and Y. Zhao, "MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science," https://omanscience.com/en/articles/metapersona-task-grounded-synthetic-populations-from-empirical-social-science.