发表机构
University of Oxford; PrincInt; FAIR at Meta; Carnegie Mellon University; University of Washington; Northwestern University; Harvard University（牛津大学; PrincInt（注：无通用标准译名，保留原名）; Meta人工智能研究院; 卡内基梅隆大学; 华盛顿大学; 西北大学; 哈佛大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对模拟增强生成（SAGE）的效率问题，提出基于度量比例公正表示+（mPJR+）公理的首次形式化，证明双重缩减模拟与路由仍保近似比例表示，并在两个领域验证算法优于基线。
AI 中文摘要
模拟增强生成（SAGE）是一项近期的技术提案，其中模型在推理时模拟个体的观点，以便对有争议的用户查询提供更具代表性的答案。SAGE 的一个核心挑战是使推理时模拟高效，同时不牺牲表示质量。我们首次对此问题进行了形式化，基于比例聚类中的一个公理，即度量比例公正表示+（mPJR+），这是已知的、基于质心聚类总能满足的最强比例性公理。我们证明，为了在给定提示上比例性地代表 $n_H$ 个人类群体的观点，我们只需创建 $n \ll n_H$ 个个体的模拟，并且在推理时，仅需根据提示动态路由到这些模拟中的 $k \ll n$ 个。这种双重缩减仍能为整个群体提供近似的比例表示保证。在实验上，跨两个领域——政治问题和个人建议——我们提出的路由算法比基于 $k$-均值或随机选择的基线实现了更高的 mPJR+ 满足率。
英文摘要
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.
CommentsAccepted at NeurIPS 2026
