Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era

TL;DR

This paper explores the unique needs of blind and low-vision users for accessible explainable AI, emphasizing multimodal explanations, blame-awareness, and participatory design to improve trust and usability.

Contribution

It provides a comprehensive analysis of BLV users' XAI requirements, highlighting modality gaps and proposing a research agenda for accessible, agentic AI systems.

Findings

BLV users value conversational explanations highly

A significant modality gap exists in current XAI systems for BLV users

BLV users often experience self-blame for AI failures

Abstract

Explainable Artificial Intelligence (XAI) is critical for ensuring trust and accountability, yet its development remains predominantly visual. For blind and low-vision (BLV) users, the lack of accessible explanations creates a fundamental barrier to the independent use of AI-driven assistive technologies. This problem intensifies as AI systems shift from single-query tools into autonomous agents that take multi-step actions and make consequential decisions across extended task horizons, where a single undetected error can propagate irreversibly before any feedback is available. This paper investigates the unique XAI requirements of the BLV community through a comprehensive analysis of user interviews and contemporary research. By examining usage patterns across environmental perception and decision support, we identify a significant modality gap. Empirical evidence suggests that while BLV users highly value conversational explanations, they frequently experience "self-blame" for AI failures. The paper concludes with a research agenda for accessible Explainable AI in agentic systems, advocating for multimodal interfaces, blame-aware explanation design, and participatory development.