# Social Choice Foundations for Simulation-Augmented Generation

arXiv: https://arxiv.org/abs/2609.38287 · HTML: https://mlsanity.com/paper/2609.38287/

## 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 (most cited first, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [Proportionally Fair Clustering](https://mlsanity.com/paper/1905.03674/) (2019)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [Axioms for AI Alignment from Human Feedback](https://mlsanity.com/paper/2405.14758/) (2024)
- [Generative Social Choice](https://mlsanity.com/paper/2309.01291/) (2023)
- [Justified Representation in Approval-Based Committee Voting](https://mlsanity.com/paper/1407.8269/) (2014)
- [Finetuning LLMs for Human Behavior Prediction in Social Science Experiments](https://mlsanity.com/paper/2509.05830/) (2025)
- [LoRe: Personalizing LLMs via Low-Rank Reward Modeling](https://mlsanity.com/paper/2504.14439/) (2025)
- [Proportional Participatory Budgeting with Additive Utilities](https://mlsanity.com/paper/2008.13276/) (2020)
- [HumanLM: Simulating Users with State Alignment Beats Response Imitation](https://mlsanity.com/paper/2603.03303/) (2026)
- [Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?](https://mlsanity.com/paper/2505.23749/) (2025)
- [Democratic Policy Development using Collective Dialogues and AI](https://mlsanity.com/paper/2311.02242/) (2023)
- [Jackpot! Alignment as a Maximal Lottery](https://mlsanity.com/paper/2501.19266/) (2025)
- [Who's in Charge? Disempowerment Patterns in Real-World LLM Usage](https://mlsanity.com/paper/2601.19062/) (2026)
- [Proportional Fairness in Clustering: A Social Choice Perspective](https://mlsanity.com/paper/2310.18162/) (2023)
- [Generative Social Choice: The Next Generation](https://mlsanity.com/paper/2505.22939/) (2025)
- [A semantic embedding space based on large language models for modelling human beliefs](https://mlsanity.com/paper/2408.07237/) (2024)
- [Proportionally Representative Clustering](https://mlsanity.com/paper/2304.13917/) (2023)
- [Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders](https://mlsanity.com/paper/2503.01769/) (2025)
- [Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy](https://mlsanity.com/paper/2605.01642/) (2026)
- [Embeddings for Preferences, Not Semantics](https://mlsanity.com/paper/2605.08360/) (2026)

## 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.