# Generative Social Choice: The Next Generation

arXiv: https://arxiv.org/abs/2505.22939 · HTML: https://mlsanity.com/paper/2505.22939/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 20 of 20)

- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Generative Social Choice](https://mlsanity.com/paper/2309.01291/) (2023)
- [Justified Representation in Approval-Based Committee Voting](https://mlsanity.com/paper/1407.8269/) (2014)
- [Opportunities and Risks of LLMs for Scalable Deliberation with Polis](https://mlsanity.com/paper/2306.11932/) (2023)
- [Multi-Winner Voting with Approval Preferences](https://mlsanity.com/paper/2007.01795/) (2020)
- [Proportional Participatory Budgeting with Additive Utilities](https://mlsanity.com/paper/2008.13276/) (2020)
- [Participatory Budgeting: Models and Approaches](https://mlsanity.com/paper/2003.00606/) (2020)
- [Robust and Verifiable Proportionality Axioms for Multiwinner Voting](https://mlsanity.com/paper/2302.01989/) (2023)
- [Fair Allocation of Indivisible Public Goods](https://mlsanity.com/paper/1805.03164/) (2018)
- [Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking](https://mlsanity.com/paper/2411.06116/) (2024)
- [Democratic Policy Development using Collective Dialogues and AI](https://mlsanity.com/paper/2311.02242/) (2023)
- [The Core of the Participatory Budgeting Problem](https://mlsanity.com/paper/1610.03474/) (2016)
- [Representation with Incomplete Votes](https://mlsanity.com/paper/2211.15608/) (2022)
- ['Generative CI' through Collective Response Systems](https://mlsanity.com/paper/2302.00672/) (2023)
- [Proportional Fairness in Clustering: A Social Choice Perspective](https://mlsanity.com/paper/2310.18162/) (2023)
- [The (Computational) Social Choice Take on Indivisible Participatory Budgeting](https://mlsanity.com/paper/2303.00621/) (2023)
- [Neutralizing Self-Selection Bias in Sampling for Sortition](https://mlsanity.com/paper/2006.10498/) (2020)
- [The Condorcet Principle for Multiwinner Elections: From Shortlisting to Proportionality](https://mlsanity.com/paper/1701.08023/) (2017)
- [Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions](https://mlsanity.com/paper/2305.11460/) (2023)

## Built on by (most cited first, 10 of 10)

- [Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values](https://mlsanity.com/paper/2506.00079/) (2025)
- [Question the Questions: Auditing Representation in Online Deliberative Processes](https://mlsanity.com/paper/2511.04588/) (2025)
- [AI Alignment From Social Choice Perspectives](https://mlsanity.com/paper/2606.21550/) (2026)
- [Collaborating with GenAI: Incentives and Replacements](https://mlsanity.com/paper/2508.20213/) (2025)
- [Generating Fair Consensus Statements with Social Choice on Token-Level MDPs](https://mlsanity.com/paper/2510.14106/) (2025)
- [Finding Common Ground in a Sea of Alternatives](https://mlsanity.com/paper/2603.16751/) (2026)
- [Embeddings for Preferences, Not Semantics](https://mlsanity.com/paper/2605.08360/) (2026)
- [CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict](https://mlsanity.com/paper/2605.28369/) (2026)
- [SNAP: A Self-Consistent Agreement Principle with Application to Robust Computation](https://mlsanity.com/paper/2602.02013/) (2026)
- [Social Choice Foundations for Simulation-Augmented Generation](https://mlsanity.com/paper/2609.38287/) (2026)

## Abstract (arXiv)

A key task in certain democratic processes is to produce a concise slate of statements that proportionally represents the full spectrum of user opinions. This task is similar to committee elections, but unlike traditional settings, the candidate set comprises all possible statements of varying lengths, and so it can only be accessed through specific queries. Combining social choice and large language models, prior work has approached this challenge through a framework of generative social choice. We extend the framework in two fundamental ways, providing theoretical guarantees even in the face of approximately optimal queries and a budget limit on the overall length of the slate. Using GPT-4o to implement queries, we showcase our approach on datasets related to city improvement measures and drug reviews, demonstrating its effectiveness in generating representative slates from unstructured user opinions.