See What I Mean? CUE: A Cognitive Model of Understanding Explanations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911167352406016 |
|---|---|
| author | Labarta, Tobias Hoang, Nhi Weitz, Katharina Samek, Wojciech Lapuschkin, Sebastian Weber, Leander |
| author_facet | Labarta, Tobias Hoang, Nhi Weitz, Katharina Samek, Wojciech Lapuschkin, Sebastian Weber, Leander |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14775 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | See What I Mean? CUE: A Cognitive Model of Understanding Explanations Labarta, Tobias Hoang, Nhi Weitz, Katharina Samek, Wojciech Lapuschkin, Sebastian Weber, Leander Human-Computer Interaction Artificial Intelligence Machine Learning 68T05, 91E30, 68U35, 62P10 H.5.2; I.2.6; H.1.2; I.4.9; K.4.2 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. |
| title | See What I Mean? CUE: A Cognitive Model of Understanding Explanations |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning 68T05, 91E30, 68U35, 62P10 H.5.2; I.2.6; H.1.2; I.4.9; K.4.2 |
| url | https://arxiv.org/abs/2506.14775 |