Jul 2026
ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
ConceptSMILE provides an independent audit layer for evaluating the trustworthiness of concept-based XAI, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations.
Mohadeseh Mollapour, K. Aslansefat, Zeinab Dehghani et al.
· arXiv.org · 0 citations