Metraipolis › archive › dc_46eb3fc46146

Adaptive Resource Allocation for Effective and Efficient LLM Social Survey Simulation — arXiv:2609.35216

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35216
License (as archived)
CC0-1.0
Archived
2026-10-07T22:13:43.200Z
SHA-256 of the archived text
04ac55ea3b933760a501415ba22d8d3660a0f5d922ce50e9fdbc4e2a498f38d1
Stable URL of this page
https://metraipolis.com/documento/dc_46eb3fc46146

How to cite

Adaptive Resource Allocation for Effective and Efficient LLM Social Survey Simulation — arXiv:2609.35216 — arXiv (en), https://arxiv.org/abs/2609.35216 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46eb3fc46146 (Metraipolis archive dc_46eb3fc46146, sha256 04ac55ea3b933760a501415ba22d8d3660a0f5d922ce50e9fdbc4e2a498f38d1)
BibTeX
@misc{dc46eb3fc46146,
  title = {Adaptive Resource Allocation for Effective and Efficient LLM Social Survey Simulation — arXiv:2609.35216},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35216},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46eb3fc46146; sha256 04ac55ea3b933760a501415ba22d8d3660a0f5d922ce50e9fdbc4e2a498f38d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35216. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) enable scalable social survey simulation, yet existing pipelines typically use the same strong general-purpose model and a fixed, often large, respondent history for every respondent-question request. This uniform approach overlooks three factors. First, stronger models may rely on their own knowledge rather than respondent-specific evidence while costing more. Second, additional history can help when evidence is limited, but irrelevant responses may add noise and increase input length. Third, the preferred model and history budget can depend on each other. We propose E2Sim, an adaptive resource allocation framework that jointly selects a model and history budget for each request. Given a respondent persona, ranked response history, and target question, a lightweight policy predicts the accuracy and cost of each configuration and selects the most suitable one. We use respondent-history drop-and-swap augmentation to improve robustness to incomplete or variable histories, and a margin-based curriculum that progresses from easier allocation decisions to harder ones. Experiments on four real-world social survey datasets, multiple model pools, and different history-budget spaces show improvements over the oracle best-fixed configurations, with accuracy gains of up to 6.3 percentage points and cost reductions of up to 55.3 percent. Code is available at this https URL .

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.35216 — 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 2026-10-07T21:55:04.252Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).