Artificial Delegates Resolve Fairness Issues in Perpetual Voting with Partial Turnout

TL;DR

This paper introduces Artificial Delegates, preference-learning agents designed to address fairness issues caused by partial voter turnout in perpetual voting systems, demonstrating their effectiveness in improving fairness and robustness.

Contribution

It proposes integrating Artificial Delegates into perpetual voting to mitigate fairness issues due to absenteeism, a novel approach in this context.

Findings

Artificial Delegates improve fairness under partial turnout.

Absenteeism significantly impacts representativeness.

Delegates enhance robustness across different voting scenarios.

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.