{"total":314,"rows":[{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236,"area":"diffusion"},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159,"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":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","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":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"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":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2106.05303","title":"Explaining Time Series Predictions with Dynamic Masks","created":"2021-06-09","cited_by_count":73,"area":null},{"id":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"area":null},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64,"area":null},{"id":"2103.04244","title":"Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications","created":"2021-03-07","cited_by_count":59,"area":null},{"id":"2101.08758","title":"How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations","created":"2021-01-21","cited_by_count":58,"area":null},{"id":"2103.11972","title":"Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals","created":"2021-03-22","cited_by_count":55,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2203.06877","title":"Rethinking Stability for Attribution-based Explanations","created":"2022-03-14","cited_by_count":52,"area":null},{"id":"2207.02739","title":"Robust Counterfactual Explanations for Tree-Based Ensembles","created":"2022-07-06","cited_by_count":49,"area":null},{"id":"2101.07685","title":"GLocalX -- From Local to Global Explanations of Black Box AI Models","created":"2021-01-19","cited_by_count":48,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47,"area":null},{"id":"2305.11997","title":"Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees","created":"2023-05-19","cited_by_count":45,"area":null},{"id":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41,"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":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39,"area":"lr"},{"id":"2101.09126","title":"Will Artificial Intelligence supersede Earth System and Climate Models?","created":"2021-01-22","cited_by_count":37,"area":null},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36,"area":null},{"id":"2209.13429","title":"WeightedSHAP: analyzing and improving Shapley based feature attributions","created":"2022-09-27","cited_by_count":36,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"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":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"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":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2110.09167","title":"RKHS-SHAP: Shapley Values for Kernel Methods","created":"2021-10-18","cited_by_count":30,"area":null},{"id":"2212.11737","title":"The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations","created":"2022-12-22","cited_by_count":29,"area":null},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","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":"2106.14648","title":"On Locality of Local Explanation Models","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2306.15786","title":"An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning","created":"2023-06-27","cited_by_count":25,"area":null},{"id":"2209.06528","title":"Explainable AI for clinical and remote health applications: a survey on tabular and time series data","created":"2022-09-14","cited_by_count":24,"area":null},{"id":"2106.08641","title":"Best of both worlds: local and global explanations with human-understandable concepts","created":"2021-06-16","cited_by_count":22,"area":null},{"id":"2109.01401","title":"CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models","created":"2021-09-03","cited_by_count":20,"area":null},{"id":"2203.06487","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","created":"2022-03-12","cited_by_count":20,"area":null},{"id":"2205.15834","title":"Attribution-based Explanations that Provide Recourse Cannot be Robust","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"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":"2206.10833","title":"Robust Bayesian Recourse","created":"2022-06-22","cited_by_count":18,"area":null},{"id":"2104.13299","title":"From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence","created":"2021-04-27","cited_by_count":17,"area":null},{"id":"2110.07550","title":"The Irrationality of Neural Rationale Models","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2305.02305","title":"Calibrated Explanations: with Uncertainty Information and Counterfactuals","created":"2023-05-03","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":"2201.10528","title":"Explainability in Music Recommender Systems","created":"2022-01-25","cited_by_count":15,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2205.00130","title":"ExSum: From Local Explanations to Model Understanding","created":"2022-04-30","cited_by_count":15,"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":"2305.10496","title":"Incorporating Attribution Importance for Improving Faithfulness Metrics","created":"2023-05-17","cited_by_count":14,"area":"lr"},{"id":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2209.14974","title":"Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification","created":"2022-09-26","cited_by_count":12,"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":"2411.09973","title":"Establishing and Evaluating Trustworthy AI: Overview and Research Challenges","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2206.00700","title":"RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model","created":"2022-06-01","cited_by_count":11,"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":"2307.05104","title":"A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI","created":"2023-07-11","cited_by_count":11,"area":null},{"id":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2605.29184","title":"Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback","created":"2026-05-27","cited_by_count":11,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2209.07559","title":"Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning","created":"2022-09-15","cited_by_count":10,"area":null},{"id":"2210.02795","title":"Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions","created":"2022-10-06","cited_by_count":10,"area":null},{"id":"2305.12351","title":"Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack","created":"2023-05-21","cited_by_count":10,"area":null},{"id":"2103.06254","title":"Interpretable Machine Learning: Moving From Mythos to Diagnostics","created":"2021-03-10","cited_by_count":9,"area":null},{"id":"2106.03820","title":"Accurate Shapley Values for explaining tree-based models","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2109.03011","title":"LEAF: Navigating Concept Drift in Cellular Networks","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2204.00492","title":"Provable concept learning for interpretable predictions using variational autoencoders","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2210.08906","title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2406.01943","title":"Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMs","created":"2024-06-04","cited_by_count":9,"area":null},{"id":"2207.12782","title":"An Explainable Decision Support System for Predictive Process Analytics","created":"2022-07-26","cited_by_count":8,"area":null},{"id":"2212.02506","title":"This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy","created":"2022-12-05","cited_by_count":8,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","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":"2407.13281","title":"Auditing Local Explanations is Hard","created":"2024-07-18","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":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"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":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2111.04303","title":"Defense Against Explanation Manipulation","created":"2021-11-08","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":"2202.07952","title":"TimeREISE: Time-series Randomized Evolving Input Sample Explanation","created":"2022-02-16","cited_by_count":6,"area":null},{"id":"2206.12481","title":"Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2209.13710","title":"Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge","created":"2022-09-27","cited_by_count":6,"area":"lr"},{"id":"2210.02419","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","created":"2022-10-05","cited_by_count":6,"area":null}],"next_cursor":"100"}