Metraipolis › archive › dc_70b58fa2a816

Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles — arXiv:2611.08730

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08730
License (as archived)
CC0-1.0
Archived
2026-11-09T22:35:51.967Z
SHA-256 of the archived text
9e5429f0403d0b4d1ddca0620fca3659df4d499d66a861c8d4ea210f0831c009
Stable URL of this page
https://metraipolis.com/documento/dc_70b58fa2a816

How to cite

Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles — arXiv:2611.08730 — arXiv (en), https://arxiv.org/abs/2611.08730 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70b58fa2a816 (Metraipolis archive dc_70b58fa2a816, sha256 9e5429f0403d0b4d1ddca0620fca3659df4d499d66a861c8d4ea210f0831c009)
BibTeX
@misc{dc70b58fa2a816,
  title = {Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles — arXiv:2611.08730},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08730},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70b58fa2a816; sha256 9e5429f0403d0b4d1ddca0620fca3659df4d499d66a861c8d4ea210f0831c009},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08730. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based digital twins aim to predict how individuals would respond in new settings from representations of their prior responses. Existing evidence that compression of survey histories need not reduce predictive accuracy suggests that representation structure, rather than information volume alone, may be an important design choice. We study BDE, a fixed representation that organizes each respondent's survey history into Background, Decision procedure, and Evaluation. We evaluate it on Twin-2K-500 (Toubia et al., 2025) by predicting each respondent's held-out answers on 17 tasks. In a paired evaluation with 100 respondents, a fully inferred BDE profile improves overall accuracy over the raw survey transcript by 1.27 percentage points (pp) on gpt-5.4-nano (p < 0.01) and 1.19 pp on gpt-5.4-mini (p < 0.001). Three analyses then examine the schema, extraction depth, and component composition. Against a length-matched free-form profile written from the same transcript by the same extractor, BDE improves pricing accuracy on both simulators (2.15 pp on nano, p < 0.01; 1.38 pp on mini, p < 0.05), while its overall advantage is significant only on nano (1.05 pp, p < 0.05). Allowing deeper inference during extraction yields no statistically significant gain on either simulator. By contrast, adding Evaluation to a Background--Decision procedure profile improves overall accuracy by 1.44 pp on nano (p < 0.001) and 1.22 pp on mini (p < 0.001). These results indicate that the advantage over raw transcripts is not explained by compression or length alone, and attribute it primarily to profile composition rather than deeper extraction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.08730 — 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 2026-11-09T22:31:01.942Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).