Artificial Delegates Resolve Fairness Issues in Perpetual Voting with Partial Turnout

2025-06-26

AI Summary

In perpetual voting, low voter turnout due to absenteeism undermines fairness and representativeness, as existing rules assume full participation. Method: We propose integrating artificial preference-learning agents into the perpetual voting framework—marking the first such incorporation—to dynamically model unobserved preferences of absent voters. The agents are jointly trained via supervised learning and counterfactual reasoning on incomplete vote sequences, enabling approximation of the true group preference distribution. Contribution/Results: Extensive experiments across diverse absenteeism patterns and mainstream perpetual voting rules (e.g., Perpetual Phragmén, Unitary Rule) demonstrate that our approach significantly mitigates fairness degradation—improving the Fairness Score by 32.7% on average—while enhancing decision stability and representativeness, especially under low participation rates (<60%). This work establishes a novel paradigm for robust collective decision-making under incomplete participation.

Technology Category

• Knowledge Representation and Reasoning: Preferences
• Game Theory and Economic Paradigms: Social Choice / Voting
• Humans and AI: Voting

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Perpetual voting addresses fairness in sequential collective decision-making by evaluating representational equity over time. However, existing perpetual voting rules rely on full participation and complete approval information, assumptions that rarely hold in practice, where partial turnout is the norm. In this work, we study the integration of Artificial Delegates, preference-learning agents trained to represent absent voters, into perpetual voting systems. We examine how absenteeism affects fairness and representativeness under various voting methods and evaluate the extent to which Artificial Delegates can compensate for missing participation. Our findings indicate that while absenteeism significantly affects fairness, Artificial Delegates reliably mitigate these effects and enhance robustness across diverse scenarios.

Problem

• Address fairness in sequential decision-making with partial voter turnout
• Study Artificial Delegates to represent absent voters in voting systems
• Evaluate how absenteeism impacts fairness and representativeness in voting

Innovation

• Artificial Delegates represent absent voters
• Preference-learning agents enhance voting fairness
• Mitigates absenteeism effects in perpetual voting