Metraipolis › archive › dc_b8ded0c22845

MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science — arXiv:2609.38392

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38392
License (as archived)
CC0-1.0
Archived
2026-10-07T12:41:47.929Z
SHA-256 of the archived text
46f88e6e1a1b560781d2b018ef94b288b523472e0aa7238b564e664314ee22ee
Stable URL of this page
https://metraipolis.com/documento/dc_b8ded0c22845

How to cite

MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science — arXiv:2609.38392 — arXiv (en), https://arxiv.org/abs/2609.38392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8ded0c22845 (Metraipolis archive dc_b8ded0c22845, sha256 46f88e6e1a1b560781d2b018ef94b288b523472e0aa7238b564e664314ee22ee)
BibTeX
@misc{dcb8ded0c22845,
  title = {MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science — arXiv:2609.38392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8ded0c22845; sha256 46f88e6e1a1b560781d2b018ef94b288b523472e0aa7238b564e664314ee22ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38392 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:14:13.621Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).