# Finding Common Ground in a Sea of Alternatives

arXiv: https://arxiv.org/abs/2603.16751 · HTML: https://mlsanity.com/paper/2603.16751/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Axioms for AI Alignment from Human Feedback](https://mlsanity.com/paper/2405.14758/) (2024)
- [Opportunities and Risks of LLMs for Scalable Deliberation with Polis](https://mlsanity.com/paper/2306.11932/) (2023)
- [Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks](https://mlsanity.com/paper/2405.01719/) (2024)
- [Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking](https://mlsanity.com/paper/2411.06116/) (2024)
- [Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?](https://mlsanity.com/paper/2505.23749/) (2025)
- [Birdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformation](https://mlsanity.com/paper/2210.15723/) (2022)
- [Bridging Systems: Open Problems for Countering Destructive Divisiveness across Ranking, Recommenders, and Governance](https://mlsanity.com/paper/2301.09976/) (2023)
- [Democratic Policy Development using Collective Dialogues and AI](https://mlsanity.com/paper/2311.02242/) (2023)
- [Community notes reduce engagement with and diffusion of false information online](https://mlsanity.com/paper/2502.13322/) (2025)
- [Generative Social Choice: The Next Generation](https://mlsanity.com/paper/2505.22939/) (2025)
- [A Quantitative and Qualitative Analysis of the Robustness of (Real-World) Election Winners](https://mlsanity.com/paper/2208.13760/) (2022)
- [Metritocracy: Representative Metrics for Lite Benchmarks](https://mlsanity.com/paper/2506.09813/) (2025)
- [Single-Winner Voting with Alliances: Avoiding the Spoiler Effect](https://mlsanity.com/paper/2401.16399/) (2024)
- [The Proportional Veto Principle for Approval Ballots](https://mlsanity.com/paper/2505.01395/) (2025)

## Built on by (most cited first, 1 of 1)

- [Embeddings for Preferences, Not Semantics](https://mlsanity.com/paper/2605.08360/) (2026)

## Abstract (arXiv)

We study the problem of selecting a statement that finds common ground across diverse population preferences. Generative AI is uniquely suited for this task because it can access a practically infinite set of statements, but AI systems like the Habermas machine leave the choice of generated statement to a voting rule. What it means for this rule to find common ground, however, is not well-defined. In this work, we propose a formal model for finding common ground in the infinite alternative setting based on the proportional veto core from social choice. To provide guarantees relative to these infinitely many alternatives and a large population, we wish to satisfy a notion of proportional veto core using only query access to the unknown distribution of alternatives and voters. We design an efficient sampling-based algorithm that returns an alternative in the (approximate) proportional veto core with high probability and prove matching lower bounds, which show that no algorithm can do the same using fewer queries. On a synthetic dataset of preferences over text, we confirm the effectiveness of our sampling-based algorithm and compare other social choice methods as well as LLM-based methods in terms of how reliably they produce statements in the proportional veto core.