conceptsmile-702b1e1f·1 events·first seen Aliases: ConceptSMILE
Researchers introduce ConceptSMILE, a model-agnostic framework for auditing the trustworthiness of concept-based explainable AI systems. The framework extends perturbation-based logic from feature-level attribution to concept-level explanations, using an XGBoost surrogate to approximate local concept behavior and assessing reliability via attribution accuracy, surrogate fidelity, faithfulness, stability, and consistency. Evaluation on retinal fundus images compares MedSAM-derived visual concepts against VLM-based semantic concepts, finding that reliability varies meaningfully across concept types and pathways.