想验证AI解释的可信度？ConceptSMILE能审计概念级解释的可靠性，MedSAM和VLM在不同维度各有优劣，论文给出了量化证据。
ConceptSMILE是一个模型无关的扰动审计框架，用于评估概念级可解释AI的可靠性。它扩展SMILE的特征级归因逻辑，通过扰动输入区域、测量概念响应变化、应用局部加权并拟合XGBoost代理来近似局部概念行为。在视网膜眼底图像上，MedSAM视觉概念在空间归因和代理保真度上表现最佳（R²=0.8503，R_w²=0.8465），而VLM语义概念在血管任务忠实性和特定伪影条件下稳定性更强。该框架为概念级XAI提供了独立的信任度审计层。
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 fits an XGBoost surrogate to approximate local concept behaviour. Reliability is assessed through attribution accuracy, surrogate fidelity, faithfulness, stability, and consistency. We evaluate ConceptSMILE on retinal fundus images by comparing MedSAM-derived visual concepts with VLM-based semantic concepts. Results show that reliability varies across concepts and pathways: MedSAM achieves stronger spatial attribution and the highest surrogate fidelity ($R^2 = 0.8503$, $R_w^2 = 0.8465$), while the VLM pathway shows stronger vessel faithfulness and stronger stability under selected artefact conditions. ConceptSMILE provides an independent audit layer for evaluating the trustworthiness of concept-based XAI.