Metraipolis › archive › dc_c54aca0e2083

Validating LLM-Generated Synthetic Survey Samples: A Use-Dependent Multi-Dimensional Framework for Social-Science Applications — arXiv:2611.00256

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00256
License (as archived)
CC0-1.0
Archived
2026-11-03T11:15:29.518Z
SHA-256 of the archived text
126caf94c367cbd6d4a53eee37e52b50650701a00223e42edf61a43667fc8ac8
Stable URL of this page
https://metraipolis.com/documento/dc_c54aca0e2083

How to cite

Validating LLM-Generated Synthetic Survey Samples: A Use-Dependent Multi-Dimensional Framework for Social-Science Applications — arXiv:2611.00256 — arXiv (en), https://arxiv.org/abs/2611.00256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c54aca0e2083 (Metraipolis archive dc_c54aca0e2083, sha256 126caf94c367cbd6d4a53eee37e52b50650701a00223e42edf61a43667fc8ac8)
BibTeX
@misc{dcc54aca0e2083,
  title = {Validating LLM-Generated Synthetic Survey Samples: A Use-Dependent Multi-Dimensional Framework for Social-Science Applications — arXiv:2611.00256},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00256},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c54aca0e2083; sha256 126caf94c367cbd6d4a53eee37e52b50650701a00223e42edf61a43667fc8ac8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) make it increasingly feasible to generate synthetic survey respondents, but their empirical usefulness cannot be judged by a single notion of accuracy. A synthetic sample may perform weakly at the respondent level while still preserving distributional or substantive relationships relevant to social-science analysis. We develop a use-dependent, multi-dimensional validation framework distinguishing predictive, distributional, and substantive validity, and illustrate it using Eurobarometer data on attitudes toward artificial intelligence. Four off-the-shelf LLMs generate responses conditional on observed respondent profiles, while supervised machine learning provides a predictive reference for interpreting their performance. The results reveal substantial differences across validation dimensions: some LLM-generated samples preserve meaningful marginal heterogeneity, demographic ordering, cross-country variation, and predictor structure despite imperfect respondent-level correspondence. Performance varies across models and outcomes, but the broader picture is cautiously constructive. Synthetic samples should therefore be evaluated against the empirical properties required by their intended use.

Tema degli esploratori: economia dei servizi IA (elenco arXiv econ.GN, nuovi lavori del giorno).
Categorie arXiv: General Economics (econ.GN).
Pagina del lavoro: https://arxiv.org/abs/2611.00256 — 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 2026-11-03T11:01:22.164Z dalla pagina https://arxiv.org/list/econ.GN/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).