Toward Valid Measurement Of (Un)fairness For Generative AI: A Proposal For Systematization Through The Lens Of Fair Equality of Chances

TL;DR

This paper proposes a structured framework based on Fair Equality of Chances to improve the validity of unfairness measurements in Generative AI, addressing contextual nuances often overlooked in existing metrics.

Contribution

It extends fairness measurement frameworks from predictive AI to GenAI, introducing a novel approach that decomposes unfairness into harm, morally arbitrary factors, and morally decisive factors.

Findings

Framework decomposes unfairness into three core components.

Analyzes factors influencing each component of unfairness.

Provides guidelines for systematizing and measuring unfairness in GenAI.

Abstract

Disparities in the societal harms and impacts of Generative AI (GenAI) systems highlight the critical need for effective unfairness measurement approaches. While numerous benchmarks exist, designing valid measurements requires proper systematization of the unfairness construct. Yet this process is often neglected, resulting in metrics that may mischaracterize unfairness by overlooking contextual nuances, thereby compromising the validity of the resulting measurements. Building on established (un)fairness measurement frameworks for predictive AI, this paper focuses on assessing and improving the validity of the measurement task. By extending existing conceptual work in political philosophy, we propose a novel framework for evaluating GenAI unfairness measurement through the lens of the Fair Equality of Chances framework. Our framework decomposes unfairness into three core constituents: the harm/benefit resulting from the system outcomes, morally arbitrary factors that should not lead to inequality in the distribution of harm/benefit, and the morally decisive factors, which distinguish subsets that can justifiably receive different treatments. By examining fairness through this structured lens, we integrate diverse notions of (un)fairness while accounting for the contextual dynamics that shape GenAI outcomes. We analyze factors contributing to each component and the appropriate processes to systematize and measure each in turn. This work establishes a foundation for developing more valid (un)fairness measurements for GenAI systems.