Explainable AI

A set of methods and design approaches that make the outputs and decision-making processes of artificial intelligence systems understandable to human users. Explainable AI aims to provide transparency about why an AI produced a particular result, typically through confidence scores, source attribution, or visual highlights. In accessibility contexts, most XAI features assume sighted users (e.g., heatmaps, saliency maps), creating a significant gap for blind users who need non-visual explanations to evaluate and trust AI output.