Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle

TL;DR

This paper explores how explainable AI can enhance fairness throughout the AI lifecycle by mapping eight fairness desiderata and discussing how XAI methods can address each, aiming to guide practical applications and future research.

Contribution

It provides a comprehensive mapping of fairness desiderata along the AI lifecycle and analyzes how XAI can help improve fairness at each stage.

Findings

Eight fairness desiderata identified and mapped along the AI lifecycle

Discussion of how XAI methods can address each fairness desideratum

Provides orientation for practical application and future research in fairness and XAI

Abstract

The widespread use of artificial intelligence (AI) systems across various domains is increasingly surfacing issues related to algorithmic fairness, especially in high-stakes scenarios. Thus, critical considerations of how fairness in AI systems might be improved -- and what measures are available to aid this process -- are overdue. Many researchers and policymakers see explainable AI (XAI) as a promising way to increase fairness in AI systems. However, there is a wide variety of XAI methods and fairness conceptions expressing different desiderata, and the precise connections between XAI and fairness remain largely nebulous. Besides, different measures to increase algorithmic fairness might be applicable at different points throughout an AI system's lifecycle. Yet, there currently is no coherent mapping of fairness desiderata along the AI lifecycle. In this paper, we we distill eight fairness desiderata, map them along the AI lifecycle, and discuss how XAI could help address each of them. We hope to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.