Towards Feminist Intersectional XAI: From Explainability to Response-Ability

TL;DR

This paper explores how feminist intersectional perspectives can reshape explainable AI by emphasizing response-ability and centering marginalized voices, proposing new research directions for ethical AI design.

Contribution

It introduces a feminist intersectional framework for XAI, emphasizing response-ability and inclusion of marginalized perspectives in AI explainability.

Findings

Feminist perspectives can enhance AI explainability by emphasizing response-ability.

Centering marginalized voices leads to more ethical and inclusive AI explanations.

Proposes initial research directions for feminist intersectional XAI.

Abstract

This paper follows calls for critical approaches to computing and conceptualisations of intersectional, feminist, decolonial HCI and AI design and asks what a feminist intersectional perspective in HCXAI research and design might look like. Sketching out initial research directions and implications for explainable AI design, it suggests that explainability from a feminist perspective would include the fostering of response-ability - the capacity to critically evaluate and respond to AI systems - and would centre marginalised perspectives.