Finding Common Ground in a Sea of Alternatives

2026-03-17

AI Summary

This work addresses the challenge of identifying consensus statements that reflect diverse group preferences in large-scale generated text, where a key obstacle is the absence of a computable definition of “consensus.” Drawing on the Proportional Veto Core from social choice theory, the paper extends this concept to infinite alternative spaces and formulates a formal model for consensus selection under unknown preference distributions. The authors propose an efficient sampling algorithm that relies solely on distributional queries and provably approximates the Proportional Veto Core with near-optimal sample complexity, complemented by a matching lower bound on query complexity. Experiments on synthetic text preference datasets demonstrate that the method significantly outperforms conventional social choice mechanisms and direct consensus generation by large language models, reliably returning high-quality consensus statements with high probability.

Technology Category

• Game Theory and Economic Paradigms: Social Choice / Voting
• Knowledge Representation and Reasoning: Preferences
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• common ground
• social choice
• proportional veto core
• preference aggregation
• generative AI

Innovation

• proportional veto core
• infinite alternatives
• sampling-based algorithm
• social choice
• generative AI