A new paper addresses the critical need for explainable AI (XAI) tailored for blind and low-vision (BLV) users, highlighting a significant modality gap in current AI systems. The research indicates that while BLV users value conversational explanations, they often blame themselves for AI failures. The paper proposes a research agenda focused on multimodal interfaces and blame-aware explanation design for agentic AI systems. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Highlights the need for inclusive AI design, potentially influencing future development of assistive technologies.
RANK_REASON Academic paper on AI explainability for a specific user group. [lever_c_demoted from research: ic=1 ai=1.0]