{"total":89,"rows":[{"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"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":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"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":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"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":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","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":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"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":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29,"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":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","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":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2111.07473","title":"Scrutinizing XAI using linear ground-truth data with suppressor variables","created":"2021-11-14","cited_by_count":18,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2104.02768","title":"Robust Semantic Interpretability: Revisiting Concept Activation Vectors","created":"2021-04-06","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":"2105.06506","title":"Sanity Simulations for Saliency Methods","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2206.08363","title":"Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2204.11642","title":"Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset","created":"2022-04-25","cited_by_count":13,"area":null},{"id":"2306.01464","title":"Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables","created":"2023-06-02","cited_by_count":12,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2211.02912","title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2305.18011","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2306.12150","title":"Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2107.00360","title":"Towards Measuring Bias in Image Classification","created":"2021-07-01","cited_by_count":6,"area":null},{"id":"2109.00707","title":"Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study","created":"2021-09-02","cited_by_count":6,"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":"2310.08537","title":"Saliency-Bench: A Comprehensive Benchmark for Evaluating Visual Explanations","created":"2023-10-12","cited_by_count":6,"area":null},{"id":"2403.12730","title":"What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks","created":"2024-03-19","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":"2104.09073","title":"Improving Attribution Methods by Learning Submodular Functions","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2112.12705","title":"Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2407.19308","title":"Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2101.07312","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2406.06609","title":"Mitigating Bias in Dataset Distillation","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2112.04882","title":"Evaluating saliency methods on artificial data with different background types","created":"2021-12-09","cited_by_count":3,"area":null},{"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":"2404.05908","title":"Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2406.17792","title":"Applications of interpretable deep learning in neuroimaging: a comprehensive review","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2104.12672","title":"A Novel Interaction-based Methodology Towards Explainable AI with Better Understanding of Pneumonia Chest X-ray Images","created":"2021-04-19","cited_by_count":2,"area":null},{"id":"2201.02155","title":"Topological Representations of Local Explanations","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2303.14608","title":"Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability","created":"2023-03-26","cited_by_count":2,"area":null},{"id":"2309.05679","title":"Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2309.10989","title":"COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2505.06003","title":"From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","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":"2508.10490","title":"On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2512.14354","title":"Enhancing Interpretability for Vision Models via Shapley Value Optimization","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2105.02825","title":"Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2109.07869","title":"Explainability Requires Interactivity","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2205.07234","title":"Clinical outcome prediction under hypothetical interventions -- a representation learning framework for counterfactual reasoning","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2302.10764","title":"On The Coherence of Quantitative Evaluation of Visual Explanations","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2303.11111","title":"Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Risks","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2307.06963","title":"Is Task-Agnostic Explainable AI a Myth?","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2404.16495","title":"T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2411.02833","title":"Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2506.01059","title":"XAI-Units: Benchmarking Explainability Methods with Unit Tests","created":"2025-06-01","cited_by_count":1,"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":"2106.02488","title":"Evaluating Local Explanations using White-box Models","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2106.06911","title":"An Interaction-based Convolutional Neural Network (ICNN) Towards Better Understanding of COVID-19 X-ray Images","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2108.10437","title":"Longitudinal Distance: Towards Accountable Instance Attribution","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2207.04969","title":"From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2305.05111","title":"When a CBR in Hand is Better than Twins in the Bush","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2403.02368","title":"A Novel Hybrid Feature Importance and Feature Interaction Detection Framework for Predictive Optimization in Industry 4.0 Applications","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2407.12950","title":"Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI","created":"2024-07-17","cited_by_count":0,"area":null},{"id":"2502.07153","title":"Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2603.16067","title":"Attribution Upsampling should Redistribute, Not Interpolate","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.15700","title":"AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.29983","title":"Improving Adversarial Robustness of Attribution via Implicit Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.30397","title":"A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}