See What I Mean? CUE: A Cognitive Model of Understanding Explanations
This work addresses the need for human-understandable explanations in machine learning systems, especially for users with visual impairments, though it is incremental in refining existing XAI evaluation methods.
The paper tackled the problem of evaluating Explainable AI (XAI) by prioritizing cognitive accessibility over technical fidelity, particularly for visually impaired users, and found that accessibility-focused color maps like Cividis did not mitigate and sometimes worsened confidence and effort gaps in a study with 455 participants.
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.