{"total":136,"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":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"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":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"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":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"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":"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":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"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":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2312.14223","title":"Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation","created":"2023-12-21","cited_by_count":41,"area":null},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2202.10553","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","created":"2022-02-16","cited_by_count":35,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","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":"2205.05126","title":"A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2111.08230","title":"Selective Ensembles for Consistent Predictions","created":"2021-11-16","cited_by_count":23,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2110.00603","title":"Algorithm Fairness in AI for Medicine and Healthcare","created":"2021-10-01","cited_by_count":21,"area":null},{"id":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21,"area":null},{"id":"2110.14297","title":"Revisiting Sanity Checks for Saliency Maps","created":"2021-10-27","cited_by_count":20,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2112.02646","title":"Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2206.02256","title":"Use-Case-Grounded Simulations for Explanation Evaluation","created":"2022-06-05","cited_by_count":19,"area":null},{"id":"2108.03388","title":"Jointly Attacking Graph Neural Network and its Explanations","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2412.12386","title":"Interpretable LLM-based Table Question Answering","created":"2024-12-16","cited_by_count":18,"area":null},{"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":"2203.02586","title":"Concept-based Explanations for Out-Of-Distribution Detectors","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2307.12344","title":"Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?","created":"2023-07-23","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":"2205.12423","title":"Deletion and Insertion Tests in Regression Models","created":"2022-05-25","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":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2105.04505","title":"Towards Benchmarking the Utility of Explanations for Model Debugging","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2205.08452","title":"A Psychological Theory of Explainability","created":"2022-05-17","cited_by_count":10,"area":null},{"id":"2302.02169","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","created":"2023-02-04","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":"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":"2412.14097","title":"Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2107.08756","title":"Attribution of Predictive Uncertainties in Classification Models","created":"2021-07-19","cited_by_count":8,"area":null},{"id":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","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":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2410.22598","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2107.02033","title":"Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2205.06905","title":"Perspectives on Incorporating Expert Feedback into Model Updates","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2206.10611","title":"Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2311.14435","title":"Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2201.04204","title":"Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems","created":"2022-01-11","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":"2303.01576","title":"DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2304.11749","title":"Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?","created":"2023-04-23","cited_by_count":6,"area":null},{"id":"2404.16042","title":"How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps","created":"2024-04-03","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":"2504.03736","title":"Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators","created":"2025-04-01","cited_by_count":6,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2309.13965","title":"May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2310.10702","title":"Transparent Anomaly Detection via Concept-based Explanations","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2404.05238","title":"Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy","created":"2024-04-08","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":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","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":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2209.01352","title":"Improving Compositional Generalization in Math Word Problem Solving","created":"2022-09-03","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":"2305.12809","title":"Relabeling Minimal Training Subset to Flip a Prediction","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2312.06032","title":"Evaluating the Utility of Model Explanations for Model Development","created":"2023-12-10","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":"2112.12444","title":"More Than Words: Towards Better Quality Interpretations of Text Classifiers","created":"2021-12-23","cited_by_count":2,"area":null},{"id":"2205.02102","title":"Concept Activation Vectors for Generating User-Defined 3D Shapes","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2305.15698","title":"Rethinking Diversity in Deep Neural Network Testing","created":"2023-05-25","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":"2310.18496","title":"How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2311.05143","title":"SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training","created":"2023-11-09","cited_by_count":2,"area":null},{"id":"2408.01715","title":"Joint Universal Adversarial Perturbations with Interpretations","created":"2024-08-03","cited_by_count":2,"area":null}],"next_cursor":"100"}