提出认知理解解释模型CUE，揭示可解释性与用户认知的关系。
See What I Mean? CUE: A Cognitive Model of Understanding Explanations
- 构建认知理解解释模型，关联可读性、可理解性与感知过程。
- 455人实验发现色觉障碍用户信心更低，助视色图反而加重负担。
- 支持自适应可解释界面设计，适合残障用户研究者参考。
随着机器学习系统在关键决策中广泛应用，对人类可理解的解释需求日益增长。当前可解释人工智能（XAI）评估常侧重技术精度，忽视认知可及性，尤其影响视觉障碍用户。本文提出CUE模型，将解释特性与认知子过程（可读性：感知；可理解性：理解；可解释性：解释）相连接。在包含455名参与者的研究中，测试了不同配色方案（BWR、Cividis、Coolwarm）的热力图，发现任务表现相近，但视觉障碍用户的信心和努力程度显著降低。出乎意料的是，以可访问性优化的Cividis等色图未能缓解差距，甚至加剧问题。该结果挑战了感知优化的假设，支持自适应XAI界面的必要性。同时验证了CUE模型：改变解释可读性会影响理解效果。本文贡献包括：(1) 形式化认知理解解释模型；(2) 人本解释属性的整合定义；(3) 支持可访问、用户定制化XAI的实证证据。
原文摘要 · Abstract (English)
As machine learning systems increasingly inform critical decisions, the need for human-understandable explanations grows. Current evaluations of Explainable AI (XAI) often prioritize technical fidelity over cognitive accessibility which critically affects users, in particular those with visual impairments. We propose CUE, a model for Cognitive Understanding of Explanations, linking explanation properties to cognitive sub-processes: legibility (perception), readability (comprehension), and interpretability (interpretation). In a study (N=455) testing heatmaps with varying colormaps (BWR, Cividis, Coolwarm), we found comparable task performance but lower confidence/effort for visually impaired users. Unlike expected, these gaps were not mitigated and sometimes worsened by accessibility-focused color maps like Cividis. These results challenge assumptions about perceptual optimization and support the need for adaptive XAI interfaces. They also validate CUE by demonstrating that altering explanation legibility affects understandability. We contribute: (1) a formalized cognitive model for explanation understanding, (2) an integrated definition of human-centered explanation properties, and (3) empirical evidence motivating accessible, user-tailored XAI.
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。