cs.GTSep 29, 2026

Social Choice Foundations for Simulation-Augmented Generation

Authors: Sonja Kraiczy, Smitha Milli, Ratip Emin Berker, Avinandan Bose, Brandon Amos, Jamelle Watson-Daniels, Maximilian Nickel, Edith Elkind, +1 more

Organizations: University of Oxford · PrincInt · FAIR at Meta · Carnegie Mellon University · University of Washington · Northwestern University · Harvard University

Abstract

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 nHn_H humans on a given prompt, we need only create simulations of n≪nHn \ll n_H individuals, and at inference time, need only dynamically route to k≪nk \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 kk-means-based or random selection baselines.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction

    Sep 7, 2026Chaemin Jang, Junsik Min, Jaewoo Choi +9DeliberationLarge Language Model Decisions

  2. Simulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language Models

    Sep 28, 2026Ji Huang, Mengfei Li, Shuai ShaoSurveyLarge Language Model Responses