研究AI解释对视障用户是否友好，提出可访问的可解释AI设计方法。
Who Benefits from AI Explanations? Towards Accessible and Interpretable Systems
- 构建四步法验证包容性XAI设计，涵盖系统分类与用户画像。
- 视障用户更易理解简化解释，详细解释反而难懂。
- 多模态呈现是实现公平可解释性的关键，适合无障碍设计者。
随着AI系统在关键领域决策中日益普及，可解释性成为提升输出可理解性的手段，使用户能做出更明智的选择。然而，尽管对可解释AI（XAI）可用性兴趣日增，其对视障等残障用户的可访问性仍缺乏研究。本文通过双路径方法探究XAI中的可访问性缺口：首先，对79项研究的文献综述发现，多数XAI评估未包含残障用户，且解释多依赖视觉形式；其次，提出四阶段方法论概念验证，实现包容性XAI设计：（1）分类AI系统，（2）定义并情境化用户角色，（3）原型设计与实现，（4）专家与用户对可访问性的评估。初步结果表明，简化解释比详细解释更易被非视觉用户理解，多模态呈现是实现更公平可解释性的必要条件。
原文摘要 · Abstract (English)
As AI systems are increasingly deployed to support decision-making in critical domains, explainability has become a means to enhance the understandability of these outputs and enable users to make more informed and conscious choices. However, despite growing interest in the usability of eXplainable AI (XAI), the accessibility of these methods, particularly for users with vision impairments, remains underexplored. This paper investigates accessibility gaps in XAI through a two-pronged approach. First, a literature review of 79 studies reveals that evaluations of XAI techniques rarely include disabled users, with most explanations relying on inherently visual formats. Second, we present a four-part methodological proof of concept that operationalizes inclusive XAI design: (1) categorization of AI systems, (2) persona definition and contextualization, (3) prototype design and implementation, and (4) expert and user assessment of XAI techniques for accessibility. Preliminary findings suggest that simplified explanations are more comprehensible for non-visual users than detailed ones, and that multimodal presentation is required for more equitable interpretability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。