ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the auditing of human-understandable concept explanations. The framework perturbs input regions, measures concept-response shifts, applies locality weighting, and f
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Mohadeseh Mollapour →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”
- LinkedLinked via arxiv author · 85%Koorosh Aslansefat →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”
- LinkedLinked via arxiv author · 85%Zeinab Dehghani →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”
- LinkedLinked via arxiv author · 85%Bhupesh Kumar Mishra →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”
- LinkedLinked via arxiv author · 85%Tejal Shah →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”
- LinkedLinked via arxiv author · 85%Zhibao Mian →
“ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI”