mlsanityData to 14 Oct 2026

Generative Social Choice

arXiv 2309.01291 ↗First posted 3 Sep 2023cs.GT cs.AI cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

The mathematical study of voting, social choice theory, has traditionally only been applicable to choices among a few predetermined alternatives, but not to open-ended decisions such as collectively selecting a textual statement. We introduce generative social choice, a design methodology for open-ended democratic processes that combines the rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. Our framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We apply this framework to the problem of summarizing free-form opinions into a proportionally representative slate of opinion statements; specifically, we develop a democratic process with representation guarantees and use this process to portray the opinions of participants in a survey about abortion policy. In a trial with 100 representative US residents, we find that 84 out of 100 participants feel "excellently" or "exceptionally" represented by the slate of five statements we extracted.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 21 of its 54 references that are in the map. First posted on arXiv 3 Sep 2023.

Builds on

21 of 54 references.

References · 21

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2023Whose Opinions Do Language Models Reflect?cited by 773
  5. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  6. 2019Measuring Bias in Contextualized Word Representationscited by 276
  7. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  8. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  9. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  10. 2017A Voting-Based System for Ethical Decision Makingcited by 55
  11. 2014Justified Representation in Approval-Based Committee Votingcited by 42
  12. 2023Opportunities and Risks of LLMs for Scalable Deliberation with Poliscited by 42
9 more
  1. 2020Multi-Winner Voting with Approval Preferencescited by 37
  2. 2020Proportional Participatory Budgeting with Additive Utilitiescited by 37
  3. 2020Adapting a Kidney Exchange Algorithm to Align with Human Valuescited by 36
  4. 2014Transductive Rademacher Complexity and its Applicationscited by 25
  5. 2023Robust and Verifiable Proportionality Axioms for Multiwinner Votingcited by 23
  6. 2014On the Computation of Fully Proportional Representationcited by 14
  7. 2022Representation with Incomplete Votescited by 13
  8. 2019Approval-Based Apportionmentcited by 8
  9. 2013Achieving Fully Proportional Representation: Approximability Resultscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 8; 2025: 22; 2026: 9.

43 papers.

Sort:

By area:

  1. 2023Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHFcited by 133
  2. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedbackcited by 100
  3. 2024Truthful Aggregation of LLMs with an Application to Online Advertisingcited by 29
  4. 2024Mapping Social Choice Theory to RLHFcited by 27
  5. 2025Emergence of polarization in networks of large language model agentscited by 26
  6. 2026How RLHF Amplifies Sycophancycited by 23
  7. 2025Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontierscited by 16
  8. 2025Pairwise Calibrated Rewards for Pluralistic Alignmentcited by 14
  9. 2025Is Your LLM Overcharging You? Tokenization, Transparency, and Incentivescited by 13
  10. 2024Incentivizing Quality Text Generation via Statistical Contractscited by 10
  11. 2025Generative Social Choice: The Next Generationcited by 10
  12. 2024ProgressGym: Alignment with a Millennium of Moral Progresscited by 9
31 more
  1. 2025Strengthening Proportionality in Temporal Votingcited by 9
  2. 2024Generative AI voting: fair collective choice is resilient to LLM biases and inconsistenciescited by 8
  3. 2024Representative Social Choice: From Learning Theory to AI Alignmentcited by 8
  4. 2026Multi-User Large Language Model Agentscited by 7
  5. 2023Leveraging Large Language Models for Collective Decision-Makingcited by 6
  6. 2025Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMscited by 6
  7. 2023Algorithmic Persuasion Through Simulationcited by 4
  8. 2025Artificial Intelligence in Deliberation: The AI Penalty and the Emergence of a New Deliberative Dividecited by 4
  9. 2026AI Alignment Breaks at the Edgecited by 4
  10. 2025AI-Generated Compromises for Coalition Formationcited by 3
  11. 2025Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmapcited by 2
  12. 2025Representative Ranking for Deliberation in the Public Spherecited by 2
  13. 2025PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectivescited by 2
  14. 2025Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Valuescited by 2
  15. 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferencescited by 2
  16. 2025Question the Questions: Auditing Representation in Online Deliberative Processescited by 2
  17. 2026AI Alignment From Social Choice Perspectivescited by 2
  18. 2023LLM-augmented Preference Learning from Natural Languagecited by 1
  19. 2025Proportional Selection in Networkscited by 1
  20. 2025A Linear Theory of Multi-Winner Votingcited by 1
  21. 2026Embeddings for Preferences, Not Semanticscited by 1
  22. 2024Estimating Contribution Quality in Online Deliberations Using a Large Language Modelcited by 0
  23. 2025Data Sharing with a Generative AI Competitorcited by 0
  24. 2025CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignmentcited by 0
  25. 2025Algorithmic Shortlisting in Participatory Budgetingcited by 0
  26. 2025AI-Generated Compromises for Coalition Formation: Modeling, Simulation, and a Textual Case Studycited by 0
  27. 2025Why They Disagree: Decoding Differences in Opinions about AI Riskcited by 0
  28. 2026Can AI mediation improve democratic deliberation?cited by 0
  29. 2026Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scalingcited by 0
  30. 2026Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approachcited by 0
  31. 2026Social Choice Foundations for Simulation-Augmented Generationcited by 0