mlsanityData to 14 Oct 2026

Social Choice Foundations for Simulation-Augmented Generation

arXiv 2609.38287 ↗First posted 29 Sep 2026cs.GT cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 nH humans on a given prompt, we need only create simulations of n ll nH 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 60 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

26 of 60 references.

References · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  4. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  5. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 113
  6. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedbackcited by 100
  7. 2019Proportionally Fair Clusteringcited by 69
  8. 2025Flipping the Dialogue: Training and Evaluating User Language Modelscited by 58
  9. 2024Axioms for AI Alignment from Human Feedbackcited by 52
  10. 2023Generative Social Choicecited by 43
  11. 2014Justified Representation in Approval-Based Committee Votingcited by 42
  12. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 39
14 more
  1. 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 38
  2. 2020Proportional Participatory Budgeting with Additive Utilitiescited by 37
  3. 2026HumanLM: Simulating Users with State Alignment Beats Response Imitationcited by 37
  4. 2025Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?cited by 22
  5. 2023Democratic Policy Development using Collective Dialogues and AIcited by 17
  6. 2025Jackpot! Alignment as a Maximal Lotterycited by 17
  7. 2026Who's in Charge? Disempowerment Patterns in Real-World LLM Usagecited by 15
  8. 2023Proportional Fairness in Clustering: A Social Choice Perspectivecited by 13
  9. 2025Generative Social Choice: The Next Generationcited by 10
  10. 2024A semantic embedding space based on large language models for modelling human beliefscited by 9
  11. 2023Proportionally Representative Clusteringcited by 8
  12. 2025Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilderscited by 6
  13. 2026Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracycited by 2
  14. 2026Embeddings for Preferences, Not Semanticscited by 1

Built on by

Not cited yet.