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

arXiv: https://arxiv.org/abs/2602.03003 · HTML: https://mlsanity.com/paper/2602.03003/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [A Minimaximalist Approach to Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2401.04056/) (2024)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences](https://mlsanity.com/paper/2406.08469/) (2024)
- [Axioms for AI Alignment from Human Feedback](https://mlsanity.com/paper/2405.14758/) (2024)
- [Optimal Auctions through Deep Learning: Advances in Differentiable Economics](https://mlsanity.com/paper/1706.03459/) (2017)
- [Complexity of Mechanism Design](https://mlsanity.com/paper/1408.1486/) (2014)
- [A Permutation-Equivariant Neural Network Architecture For Auction Design](https://mlsanity.com/paper/2003.01497/) (2020)
- [SDPO: Segment-Level Direct Preference Optimization for Social Agents](https://mlsanity.com/paper/2501.01821/) (2025)
- [Optimal-er Auctions through Attention](https://mlsanity.com/paper/2202.13110/) (2022)
- [Mapping Social Choice Theory to RLHF](https://mlsanity.com/paper/2404.13038/) (2024)
- [A Scalable Neural Network for DSIC Affine Maximizer Auction Design](https://mlsanity.com/paper/2305.12162/) (2023)
- [Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences](https://mlsanity.com/paper/2405.15065/) (2024)
- [Certifying Strategyproof Auction Networks](https://mlsanity.com/paper/2006.08742/) (2020)
- [Direct Alignment with Heterogeneous Preferences](https://mlsanity.com/paper/2502.16320/) (2025)
- [Preference Restrictions in Computational Social Choice: A Survey](https://mlsanity.com/paper/2205.09092/) (2022)
- [Learning to Elect](https://mlsanity.com/paper/2108.02768/) (2021)
- [Learning to bid in revenue-maximizing auctions](https://mlsanity.com/paper/1902.10427/) (2019)
- [Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models](https://mlsanity.com/paper/2309.06375/) (2023)
- [Deep Automated Mechanism Design for Integrating Ad Auction and Allocation in Feed](https://mlsanity.com/paper/2401.01656/) (2024)
- [Learning How to Vote with Principles: Axiomatic Insights Into the Collective Decisions of Neural Networks](https://mlsanity.com/paper/2410.16170/) (2024)
- [Explainability in Mechanism Design: Recent Advances and the Road Ahead](https://mlsanity.com/paper/2206.03031/) (2022)
- [Mode Connectivity in Auction Design](https://mlsanity.com/paper/2305.11005/) (2023)
- [DeepVoting: Learning and Fine-Tuning Voting Rules with Canonical Embeddings](https://mlsanity.com/paper/2408.13630/) (2024)

## 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.