mlsanityData to 14 Oct 2026

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

arXiv 2607.09649 ↗First posted 10 Jul 2026cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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 (R2 = 0.8503, Rw2 = 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

34 of 54 references.

References · 34

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2025Qwen3-VL Technical Reportcited by 2,793
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  6. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  7. 2018Sanity Checks for Saliency Mapscited by 1,156
  8. 2020Concept Bottleneck Modelscited by 1,032
  9. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  10. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  11. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  12. 2017Interpretation of Neural Networks is Fragilecited by 444
22 more
  1. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 312
  2. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  3. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  4. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 131
  5. 2021Do Concept Bottleneck Models Learn as Intended?cited by 116
  6. 2023Probabilistic Concept Bottleneck Modelscited by 101
  7. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  8. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  9. 2021S-LIME: Stabilized-LIME for Model Explanationcited by 52
  10. 2020BayLIME: Bayesian Local Interpretable Model-Agnostic Explanationscited by 51
  11. 2022Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capabilitycited by 46
  12. 2019ALIME: Autoencoder Based Approach for Local Interpretabilitycited by 41
  13. 2018Defining Locality for Surrogates in Post-hoc Interpretablitycited by 33
  14. 2020OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithmscited by 30
  15. 2021TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Modelscited by 28
  16. 2023GLIME: General, Stable and Local LIME Explanationcited by 21
  17. 2024VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledgecited by 19
  18. 2021Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Toolscited by 9
  19. 2023Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanationscited by 8
  20. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 8
  21. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  22. 2024Mapping the Mind of an Instruction-based Image Editing using SMILEcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evian: Towards Explainable Visual Instruction-tuning Data Auditing
  2. 2026SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis
  3. 2024An Axiomatic Approach to Model-Agnostic Concept Explanations
  4. 2024FastRM: An efficient and automatic explainability framework for multimodal generative models
  5. 2025Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
  6. 2025Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
  7. 2024Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)
  8. 2026From Attribution to Action: A Human-Centered Application of Activation Steering