See What I Mean? CUE: A Cognitive Model of Understanding Explanations

TL;DR

This paper introduces CUE, a cognitive model linking explanation features to human understanding processes, and provides empirical evidence on how explanation design impacts users, especially those with visual impairments.

Contribution

It presents a formal cognitive model of explanation understanding, defines human-centered explanation properties, and offers empirical insights into accessible XAI design.

Findings

Visual impairments affect confidence and effort in understanding explanations.

Color maps designed for accessibility may not improve, and can worsen, understanding.

Altering explanation legibility influences interpretability and comprehension.

Abstract

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.