A Critical Survey on Fairness Benefits of Explainable AI

TL;DR

The paper systematically interrogates how explanations from AI models are claimed to influence fairness. By reviewing 175 articles and inductively deriving seven archetypal claims, the authors reveal that many assertions about XAI and fairness are vague, normatively under-specified, or misaligned with what current XAI methods can realistically achieve. They argue for viewing XAI as one tool within a broader sociotechnical effort to address algorithmic fairness, demanding precise specification of the XAI method, the targeted fairness desideratum, the mechanism by which fairness is enabled, and the stakeholders who benefit. This nuanced critique highlights the need to account for multidimensional fairness (formal vs perceived; distributive, procedural, informational) and to carefully consider epistemic versus substantial goals, ultimately guiding future research toward more context-aware, stakeholder-centered XAI design. The work provides a structured framework to map XAI interventions onto fairness objectives across the decision lifecycle, with implications for researchers, practitioners, and regulators aiming to deploy fairer AI systems.

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.

Figures (2)

• Figure 1: PRISMA flowchart describing the article selection procedure.
• Figure 2: The seven identified archetypal claims on the role of XAI for fairness desiderata.