mlsanityData to 7 Oct 2026

Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment

arXiv 2602.03003 ↗First posted 3 Feb 2026cs.AI cs.LGcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Social choice has become a foundational component of modern machine learning systems. From auctions and resource allocation to the alignment of large generative models, machine learning pipelines increasingly aggregate heterogeneous preferences and incentives into collective decisions. In effect, many contemporary machine learning systems already implement social choice mechanisms, often implicitly and without explicit normative scrutiny. This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data. We synthesize work across auctions, decision aggregation, and preference learning, showing how classical axioms and impossibility results reappear as objectives, constraints, and optimization trade-offs. We conclude by identifying 18 open problems defining a new research agenda at the intersection of machine learning and social choice theory.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 38 of its 82 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

38 of 82 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback16 Apr
  2. 2022Constitutional AI: Harmlessness from AI Feedback15 Dec
  3. 2020Learning to summarize from human feedback2 Sep

Other references · 35

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2017Deep Setscited by 1,394
  5. 2024A Minimaximalist Approach to Reinforcement Learning from Human Feedbackcited by 141
  6. 2023Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHFcited by 125
  7. 2024PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferencescited by 53
  8. 2024Axioms for AI Alignment from Human Feedbackcited by 50
  9. 2017Optimal Auctions through Deep Learning: Advances in Differentiable Economicscited by 38
  10. 2014Complexity of Mechanism Designcited by 33
  11. 2020A Permutation-Equivariant Neural Network Architecture For Auction Designcited by 31
  12. 2025SDPO: Segment-Level Direct Preference Optimization for Social Agentscited by 29
23 more
  1. 2022Optimal-er Auctions through Attentioncited by 26
  2. 2024Mapping Social Choice Theory to RLHFcited by 26
  3. 2023A Scalable Neural Network for DSIC Affine Maximizer Auction Designcited by 23
  4. 2024Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferencescited by 23
  5. 2020Certifying Strategyproof Auction Networkscited by 21
  6. 2025Direct Alignment with Heterogeneous Preferencescited by 19
  7. 2022Preference Restrictions in Computational Social Choice: A Surveycited by 9
  8. 2021Learning to Electcited by 8
  9. 2019Learning to bid in revenue-maximizing auctionscited by 7
  10. 2023Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Modelscited by 7
  11. 2024Deep Automated Mechanism Design for Integrating Ad Auction and Allocation in Feedcited by 6
  12. 2024Learning How to Vote with Principles: Axiomatic Insights Into the Collective Decisions of Neural Networkscited by 5
  13. 2022Explainability in Mechanism Design: Recent Advances and the Road Aheadcited by 3
  14. 2023Mode Connectivity in Auction Designcited by 3
  15. 2024DeepVoting: Learning and Fine-Tuning Voting Rules with Canonical Embeddingscited by 2
  16. 2024Learning Aggregation Rules in Participatory Budgeting: A Data-Driven Approachcited by 2
  17. 2026Differential Voting: Loss Functions For Axiomatically Diverse Aggregation of Heterogeneous Preferencescited by 2
  18. 2025Revenue-Optimal Efficient Mechanism Design with General Type Spacescited by 1
  19. 2025Deterministic-Allocation and Anonymous Joint Advertising in E-commerce Platformscited by 1
  20. 2025Fluid Democracy in Federated Data Aggregationcited by 1
  21. 2025Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?cited by 1
  22. 2025What Voting Rules Actually Do: A Data-Driven Analysis of Multi-Winner Votingcited by 1
  23. 2026Bridging the Gap Between Estimated and True Regret Towards Reliable Regret Estimation in Deep Learning based Mechanism Designcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Representative Social Choice: From Learning Theory to AI Alignment
  2. 2023Evaluating Agents using Social Choice Theory
  3. 2026Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment
  4. 2025Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
  5. 2025Adaptive Preference Aggregation
  6. 2025Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
  7. 2026Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy
  8. 2018Social Choice Random Utility Models of Intransitive Pairwise Comparisons ↗