{"total":188,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2102.09692","title":"To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making","created":"2021-02-19","cited_by_count":118,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"area":null},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2302.07265","title":"The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus","created":"2023-02-14","cited_by_count":37,"area":null},{"id":"2305.10289","title":"Explain Any Concept: Segment Anything Meets Concept-Based Explanation","created":"2023-05-17","cited_by_count":37,"area":null},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33,"area":null},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2211.12486","title":"Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2105.12837","title":"Fooling Partial Dependence via Data Poisoning","created":"2021-05-26","cited_by_count":16,"area":"safety"},{"id":"2401.10640","title":"A comprehensive study on fidelity metrics for XAI","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2409.16756","title":"Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics","created":"2024-09-25","cited_by_count":16,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2311.01961","title":"Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2404.12488","title":"Global Counterfactual Directions","created":"2024-04-18","cited_by_count":15,"area":"diffusion"},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2302.03225","title":"Efficient XAI Techniques: A Taxonomic Survey","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2303.16390","title":"Are Data-driven Explanations Robust against Out-of-distribution Data?","created":"2023-03-29","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2403.13086","title":"Listenable Maps for Audio Classifiers","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2112.10161","title":"RELAX: Representation Learning Explainability","created":"2021-12-19","cited_by_count":12,"area":null},{"id":"2311.06786","title":"Explainability of Vision Transformers: A Comprehensive Review and New Perspectives","created":"2023-11-12","cited_by_count":12,"area":null},{"id":"2411.09973","title":"Establishing and Evaluating Trustworthy AI: Overview and Research Challenges","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2106.07787","title":"Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2303.01538","title":"Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2401.06465","title":"Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2201.02445","title":"Negative Evidence Matters in Interpretable Histology Image Classification","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2305.08950","title":"Causal Analysis for Robust Interpretability of Neural Networks","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2403.07733","title":"Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2405.02383","title":"A Fresh Look at Sanity Checks for Saliency Maps","created":"2024-05-03","cited_by_count":8,"area":null},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2106.13346","title":"What will it take to generate fairness-preserving explanations?","created":"2021-06-24","cited_by_count":7,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2412.00800","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","created":"2024-12-01","cited_by_count":7,"area":null},{"id":"2502.04695","title":"Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2111.05299","title":"Can Information Flows Suggest Targets for Interventions in Neural Circuits?","created":"2021-11-09","cited_by_count":6,"area":null},{"id":"2111.09121","title":"Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach","created":"2021-11-17","cited_by_count":6,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2210.02419","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2303.13299","title":"Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2402.03348","title":"Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2404.11330","title":"Toward Understanding the Disagreement Problem in Neural Network Feature Attribution","created":"2024-04-17","cited_by_count":6,"area":null},{"id":"2405.13474","title":"Why do explanations fail? A typology and discussion on failures in XAI","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2406.05090","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2411.05841","title":"FLEXtime: Filterbank learning to explain time series","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2104.09073","title":"Improving Attribution Methods by Learning Submodular Functions","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2211.08686","title":"Improving Interpretability via Regularization of Neural Activation Sensitivity","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2303.12316","title":"TsSHAP: Robust model agnostic feature-based explainability for time series forecasting","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2305.14979","title":"Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2406.14349","title":"When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2406.15085","title":"Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2407.16653","title":"Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2407.19683","title":"Revisiting the robustness of post-hoc interpretability methods","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2501.15070","title":"Unifying Prediction and Explanation in Time-Series Transformers via Shapley-based Pretraining","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2106.07758","title":"Pitfalls of Explainable ML: An Industry Perspective","created":"2021-06-14","cited_by_count":4,"area":null},{"id":"2301.13445","title":"A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2308.03161","title":"Precise Benchmarking of Explainable AI Attribution Methods","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2404.01877","title":"Procedural Fairness in Machine Learning","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2406.01274","title":"Expected Grad-CAM: Towards gradient faithfulness","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2406.13584","title":"FreqRISE: Explaining time series using frequency masking","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2409.08655","title":"LMAC-TD: Producing Time Domain Explanations for Audio Classifiers","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2411.08013","title":"Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2412.05592","title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2504.00795","title":"Explainable AI-Based Interface System for Weather Forecasting Model","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2504.17023","title":"Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2506.05774","title":"Evaluating Neuron Explanations: A Unified Framework with Sanity Checks","created":"2025-06-06","cited_by_count":4,"area":"mechinterp"},{"id":"2509.03626","title":"Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE","created":"2025-09-03","cited_by_count":4,"area":"rag"},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2304.13836","title":"On Pitfalls of $\\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2307.09591","title":"Saliency strikes back: How filtering out high frequencies improves white-box explanations","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2310.14957","title":"XTSC-Bench: Quantitative Benchmarking for Explainers on Time Series Classification","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2311.04813","title":"Be Careful When Evaluating Explanations Regarding Ground Truth","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2312.10534","title":"Rethinking Robustness of Model Attributions","created":"2023-12-16","cited_by_count":3,"area":null},{"id":"2401.16744","title":"ShaRP: Explaining Rankings and Preferences with Shapley Values","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2405.17615","title":"Listenable Maps for Zero-Shot Audio Classifiers","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2407.12401","title":"Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2507.05916","title":"On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification","created":"2025-07-08","cited_by_count":3,"area":null}],"next_cursor":"100"}