A Survey of Accessible Explainable Artificial Intelligence Research

TL;DR

This survey reviews the current state of accessible explainable AI, highlighting the lack of inclusive methods and advocating for multimodal, universally designed explanations to promote digital inclusion for persons with disabilities.

Contribution

It systematically analyzes existing research on accessible XAI, identifies gaps, and emphasizes the need for non-visual explanation methods and inclusive design principles.

Findings

Most XAI techniques rely on visual explanations, which are inaccessible to blind users.

There is a significant lack of research on accessible XAI for diverse disabilities.

Inclusive, multimodal explanation methods are necessary for digital inclusion.

Abstract

The increasing integration of Artificial Intelligence (AI) into everyday life makes it essential to explain AI-based decision-making in a way that is understandable to all users, including those with disabilities. Accessible explanations are crucial as accessibility in technology promotes digital inclusion and allows everyone, regardless of their physical, sensory, or cognitive abilities, to use these technologies effectively. This paper presents a systematic literature review of the research on the accessibility of Explainable Artificial Intelligence (XAI), specifically considering persons with sight loss. Our methodology includes searching several academic databases with search terms to capture intersections between XAI and accessibility. The results of this survey highlight the lack of research on Accessible XAI (AXAI) and stress the importance of including the disability community in XAI development to promote digital inclusion and accessibility and remove barriers. Most XAI techniques rely on visual explanations, such as heatmaps or graphs, which are not accessible to persons who are blind or have low vision. Therefore, it is necessary to develop explanation methods through non-visual modalities, such as auditory and tactile feedback, visual modalities accessible to persons with low vision, and personalized solutions that meet the needs of individuals, including those with multiple disabilities. We further emphasize the importance of integrating universal design principles into AI development practices to ensure that AI technologies are usable by everyone.