Metraipolis › archive › dc_5edd962bcd32

Social Choice Foundations for Simulation-Augmented Generation — arXiv:2609.38287

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38287
License (as archived): CC0-1.0
Archived: 2026-10-07T12:43:29.023Z
SHA-256 of the archived text: 02bd9d390258040cd1ef030cff3c879e6832d22a6133ae8b3ff15f558e316a8b
Stable URL of this page: https://metraipolis.com/documento/dc_5edd962bcd32

How to cite

Social Choice Foundations for Simulation-Augmented Generation — arXiv:2609.38287 — arXiv (en), https://arxiv.org/abs/2609.38287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5edd962bcd32 (Metraipolis archive dc_5edd962bcd32, sha256 02bd9d390258040cd1ef030cff3c879e6832d22a6133ae8b3ff15f558e316a8b)

BibTeX

@misc{dc5edd962bcd32,
  title = {Social Choice Foundations for Simulation-Augmented Generation — arXiv:2609.38287},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38287},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5edd962bcd32; sha256 02bd9d390258040cd1ef030cff3c879e6832d22a6133ae8b3ff15f558e316a8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to provide more representative answers to contentious user queries. A core challenge for SAGE is making inference-time simulation efficient without sacrificing representation quality. We introduce the first formalization of this problem, based upon an axiom from proportional clustering known as metric proportional justified representation+ (mPJR+) which is the strongest proportionality axiom known to always be satisfiable by centroid-based clustering. We prove that to proportionally represent the viewpoints of a population of $n_H$ humans on a given prompt, we need only create simulations of $n \ll n_H$ individuals, and at inference time, need only dynamically route to $k \ll n$ of those simulations based upon the prompt. This twofold reduction still yields approximate proportional representation guarantees for the entire population. Empirically, across two domains-political questions and personal advice-our proposed routing algorithm achieves higher mPJR+ satisfaction rates than $k$-means-based or random selection baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38287 — 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 2026-10-07T12:14:13.851Z 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).