Metraipolis › archive › dc_fa94f72b4b7e

When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing — arXiv:2608.22438

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22438
License (as archived)
CC0-1.0
Archived
2026-10-18T07:41:26.549Z
SHA-256 of the archived text
d0507bb5aefe8d85b7ace312f1037a3782dc111df47d8d5a249e3fe0c0874551
Stable URL of this page
https://metraipolis.com/documento/dc_fa94f72b4b7e

How to cite

When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing — arXiv:2608.22438 — arXiv (en), https://arxiv.org/abs/2608.22438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa94f72b4b7e (Metraipolis archive dc_fa94f72b4b7e, sha256 d0507bb5aefe8d85b7ace312f1037a3782dc111df47d8d5a249e3fe0c0874551)
BibTeX
@misc{dcfa94f72b4b7e,
  title = {When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing — arXiv:2608.22438},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22438},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa94f72b4b7e; sha256 d0507bb5aefe8d85b7ace312f1037a3782dc111df47d8d5a249e3fe0c0874551},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Persona-conditioned large language models (LLMs) are increasingly used to simulate survey responses across diverse domains. However, apparent response variation can reflect unconditioned model priors or token sampling noise rather than systematic persona conditioning. We argue that persona-conditioned variation is informative when semantically similar personas exhibit concordant response shifts. To operationalize this principle, we introduce Persona-Conditioned Informativeness (PCI), an unsupervised diagnostic metric that measures whether semantically similar personas deviate in concordant directions relative to item-level sample baselines. By modeling personas as a similarity graph, PCI uses Local Moran's I to quantify local spatial coherence and extract compact persona subsets without using construct labels. To evaluate PCI without external human benchmarks, we test its ability to recover established latent value structure using the 57-item Portrait Values Questionnaire-Revised (PVQ-RR). Confirmatory factor analysis (CFA) shows that a PCI-selected 10% subset substantially improves overall construct recovery relative to response-stability and random selection. These findings support PCI as a principled internal diagnostic for screening synthetic respondents in survey pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.22438 — 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 2026-10-18T07:37:52.721Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).