{"total":47,"rows":[{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2202.05656","title":"Evaluation of post-hoc interpretability methods in time-series classification","created":"2022-02-11","cited_by_count":53,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2305.19101","title":"Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness","created":"2023-05-30","cited_by_count":20,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2104.06164","title":"Fast Hierarchical Games for Image Explanations","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2105.06506","title":"Sanity Simulations for Saliency Methods","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2206.13872","title":"When are Post-hoc Conceptual Explanations Identifiable?","created":"2022-06-28","cited_by_count":14,"area":null},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2307.15007","title":"Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2301.06989","title":"Negative Flux Aggregation to Estimate Feature Attributions","created":"2023-01-17","cited_by_count":7,"area":null},{"id":"2404.04647","title":"Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training","created":"2024-04-06","cited_by_count":7,"area":null},{"id":"2203.14265","title":"A Unified Study of Machine Learning Explanation Evaluation Metrics","created":"2022-03-27","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":"2207.07038","title":"SHAP-XRT: The Shapley Value Meets Conditional Independence Testing","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2308.00824","title":"An Exact Kernel Equivalence for Finite Classification Models","created":"2023-08-01","cited_by_count":5,"area":null},{"id":"2303.11884","title":"Better Understanding Differences in Attribution Methods via Systematic Evaluations","created":"2023-03-21","cited_by_count":4,"area":null},{"id":"2403.09480","title":"What Sketch Explainability Really Means for Downstream Tasks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2404.08069","title":"Persistent Classification: A New Approach to Stability of Data and Adversarial Examples","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2603.15656","title":"Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2405.02344","title":"A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2411.01126","title":"Axiomatic Explainer Globalness via Optimal Transport","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2601.18678","title":"Counterfactual Explanations on Robust Perceptual Geodesics","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2605.19607","title":"Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2602.08715","title":"Exploring SAIG Methods for an Objective Evaluation of XAI","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2307.10026","title":"Contextual Reliability: When Different Features Matter in Different Contexts","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2309.16452","title":"On the Trade-offs between Adversarial Robustness and Actionable Explanations","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2310.12553","title":"Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2412.16204","title":"Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2507.04788","title":"Machine Learning from Explanations","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2512.07578","title":"$\\phi$-Table: A Statistical Explanation for Global SHAP","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2605.16905","title":"AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}