Who Benefits from AI Explanations? Towards Accessible and Interpretable Systems

TL;DR

This paper explores the accessibility challenges of explainable AI, highlighting the lack of inclusive evaluation methods and proposing a framework for designing more accessible, multimodal explanations for users with vision impairments.

Contribution

It introduces a novel inclusive XAI design methodology and provides preliminary evidence that simplified and multimodal explanations improve accessibility for non-visual users.

Findings

Simplified explanations enhance comprehension for non-visual users.

Multimodal presentation improves interpretability and accessibility.

Most XAI evaluations overlook disabled users and rely on visual formats.

Abstract

As AI systems are increasingly deployed to support decision-making in critical domains, explainability has become a means to enhance the understandability of these outputs and enable users to make more informed and conscious choices. However, despite growing interest in the usability of eXplainable AI (XAI), the accessibility of these methods, particularly for users with vision impairments, remains underexplored. This paper investigates accessibility gaps in XAI through a two-pronged approach. First, a literature review of 79 studies reveals that evaluations of XAI techniques rarely include disabled users, with most explanations relying on inherently visual formats. Second, we present a four-part methodological proof of concept that operationalizes inclusive XAI design: (1) categorization of AI systems, (2) persona definition and contextualization, (3) prototype design and implementation, and (4) expert and user assessment of XAI techniques for accessibility. Preliminary findings suggest that simplified explanations are more comprehensible for non-visual users than detailed ones, and that multimodal presentation is required for more equitable interpretability.