The Perceptual Gap: Why We Need Accessible XAI for Assistive Technologies

TL;DR

This paper highlights the lack of accessible explainable AI methods tailored for users with sensory disabilities and advocates for human-centered approaches to improve AI transparency and usability for assistive technology users.

Contribution

It surveys existing XAI work emphasizing accessibility, identifies gaps for sensory-disabled users, and proposes future directions for accessible human-centered XAI.

Findings

Most XAI methods are not designed for disabled users

Current explanations are often difficult for sensory-disabled users to understand

There is a significant gap in accessible XAI research for assistive technologies

Abstract

Artificial intelligence systems are widely used by people with sensory disabilities, like loss of vision or hearing, to help perceive or navigate the world around them. This includes tasks like describing an image or object they cannot touch, reading documents, automatically captioning speech, and so on. Presently, models used for these tasks are based on deep neural networks and are thusly black boxes. Explainable AI (XAI) describes methods that can explain why a model gave the output it did. However, existing XAI methodologies are rarely accessible or designed with disabled users in mind. In this paper, we survey existing work in XAI with a focus on human-centered and accessibility-centered approaches or evaluations. We show that there is next-to-no XAI work that accounts for people with sensory disabilities, that many typical explanations are difficult for them to comprehend, and propose possible avenues for future work in Accessible Human-Centered XAI.