A Critical Survey on Fairness Benefits of Explainable AI

Abstract

In this critical survey, we analyze typical claims on the relationship between explainable AI (XAI) and fairness to disentangle the multidimensional relationship between these two concepts. Based on a systematic literature review and a subsequent qualitative content analysis, we identify seven archetypal claims from 175 scientific articles on the alleged fairness benefits of XAI. We present crucial caveats with respect to these claims and provide an entry point for future discussions around the potentials and limitations of XAI for specific fairness desiderata. Importantly, we notice that claims are often (i) vague and simplistic, (ii) lacking normative grounding, or (iii) poorly aligned with the actual capabilities of XAI. We suggest to conceive XAI not as an ethical panacea but as one of many tools to approach the multidimensional, sociotechnical challenge of algorithmic fairness. Moreover, when making a claim about XAI and fairness, we emphasize the need to be more specific about what kind of XAI method is used, which fairness desideratum it refers to, how exactly it enables fairness, and who is the stakeholder that benefits from XAI.

ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT '24)

References in corpus (18)

• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• 'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions
• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Successful Combination of Database Search and Snowballing for Identification of Primary Studies in Systematic Literature Studies
• Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• A Clarification of the Nuances in the Fairness Metrics Landscape
• On the Performance of Hybrid Search Strategies for Systematic Literature Reviews in Software Engineering
• Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations
• Wikidata as a seed for Web Extraction
• This Thing Called Fairness: Disciplinary Confusion Realizing a Value in Technology
• "There Is Not Enough Information": On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making
• Explainable Fairness in Recommendation
• Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
• Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems
• FairCanary: Rapid Continuous Explainable Fairness
• Interpretable and Fair Boolean Rule Sets via Column Generation
• How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis

Cited by in corpus (3)

• Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
• It's only fair when I think it's fair: How Gender Bias Alignment Undermines Distributive Fairness in Human-AI Collaboration
• From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring