What question did this study set out to answer?

This work aims to establish a framework for providing understandable and faithful explanations of non-interpretable AI models.

February 14, 2026Open Access

A framework for causal concept-based model explanations

Key Points

This work aims to establish a framework for providing understandable and faithful explanations of non-interpretable AI models.
Developed a conceptual framework for causal concept-based explanations.
Calculated probability of sufficiency for concept interventions to generate explanations.
Used a proof-of-concept model to demonstrate explanations on classifiers trained with the CelebA dataset.
Demonstrated clear understandability through a concept-based vocabulary.
Ensured fidelity by aligning explanation interpretation context with generation context.

Abstract

This work presents a conceptual framework for causal concept-based post-hoc explainable artificial intelligence (XAI), based on the requirements that explanations for non-interpretable models must be both understandable and faithful to the model being explained. Local and global explanations are generated by calculating the probability of sufficiency of concept interventions. Example explanations are presented, generated with a proof-of-concept model made to explain classifiers trained on the CelebA dataset. Understandability is demonstrated through a clear concept-based vocabulary, subject to an implicit causal interpretation. Fidelity is addressed by highlighting important framework assumptions, stressing that the context of explanation interpretation must align with the context of explanation generation.

A framework for causal concept-based model explanations

Key Points

Abstract

Cite This Study