{"list":"other","total":69,"rows":[{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2011.04573","title":"Parameterized Explainer for Graph Neural Network","created":"2020-11-09","cited_by_count":426},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"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},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"2010.05788","title":"PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks","created":"2020-10-12","cited_by_count":211},{"id":"1903.10464","title":"Explaining individual predictions when features are dependent: More accurate approximations to Shapley values","created":"2019-03-25","cited_by_count":208},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"1910.06358","title":"Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability","created":"2019-10-14","cited_by_count":114},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2010.13924","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","created":"2020-10-26","cited_by_count":102},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"2011.08512","title":"Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database","created":"2020-11-17","cited_by_count":96},{"id":"2009.08634","title":"On the Tractability of SHAP Explanations","created":"2020-09-18","cited_by_count":92},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91},{"id":"1802.00121","title":"Interpreting CNNs via Decision Trees","created":"2018-02-01","cited_by_count":89},{"id":"2001.03447","title":"Explaining the Explainer: A First Theoretical Analysis of LIME","created":"2020-01-10","cited_by_count":89},{"id":"2108.00783","title":"CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms","created":"2021-08-02","cited_by_count":86},{"id":"1807.02910","title":"Model Agnostic Supervised Local Explanations","created":"2018-07-09","cited_by_count":83},{"id":"2006.10965","title":"How does this interaction affect me? Interpretable attribution for feature interactions","created":"2020-06-19","cited_by_count":73},{"id":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60},{"id":"1810.09648","title":"What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play","created":"2018-10-23","cited_by_count":53},{"id":"2010.12016","title":"Towards falsifiable interpretability research","created":"2020-10-22","cited_by_count":53},{"id":"2201.10295","title":"Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts","created":"2022-01-25","cited_by_count":53},{"id":"1904.00605","title":"Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks","created":"2019-04-01","cited_by_count":49},{"id":"1908.03020","title":"Measurable Counterfactual Local Explanations for Any Classifier","created":"2019-08-08","cited_by_count":48},{"id":"1711.08998","title":"Visual Feature Attribution using Wasserstein GANs","created":"2017-11-24","cited_by_count":47},{"id":"2011.06169","title":"Robust and Stable Black Box Explanations","created":"2020-11-12","cited_by_count":47},{"id":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47},{"id":"1910.02065","title":"Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods","created":"2019-10-04","cited_by_count":38},{"id":"2302.07265","title":"The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus","created":"2023-02-14","cited_by_count":37},{"id":"1907.13054","title":"Grid Saliency for Context Explanations of Semantic Segmentation","created":"2019-07-30","cited_by_count":32},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32},{"id":"1712.06302","title":"Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks","created":"2017-12-18","cited_by_count":28},{"id":"1912.01819","title":"Counterfactual Explanation Algorithms for Behavioral and Textual Data","created":"2019-12-04","cited_by_count":26},{"id":"1512.00172","title":"Analyzing Classifiers: Fisher Vectors and Deep Neural Networks","created":"2015-12-01","cited_by_count":24},{"id":"2003.06005","title":"Model Agnostic Multilevel Explanations","created":"2020-03-12","cited_by_count":24},{"id":"2006.08287","title":"ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping","created":"2020-06-15","cited_by_count":20},{"id":"1711.10589","title":"Contextual Outlier Interpretation","created":"2017-11-28","cited_by_count":19},{"id":"2011.08596","title":"Learning outside the Black-Box: The pursuit of interpretable models","created":"2020-11-17","cited_by_count":18},{"id":"2003.01640","title":"Explaining Groups of Points in Low-Dimensional Representations","created":"2020-03-03","cited_by_count":16},{"id":"2109.01962","title":"Counterfactual Evaluation for Explainable AI","created":"2021-09-05","cited_by_count":15},{"id":"2205.14772","title":"Unfooling Perturbation-Based Post Hoc Explainers","created":"2022-05-29","cited_by_count":12},{"id":"2307.00364","title":"The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations","created":"2023-07-01","cited_by_count":12},{"id":"2307.15007","title":"Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability","created":"2023-07-27","cited_by_count":10},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","cited_by_count":9},{"id":"1906.10924","title":"Interpretable Question Answering on Knowledge Bases and Text","created":"2019-06-26","cited_by_count":8},{"id":"2105.09740","title":"Evaluating the Correctness of Explainable AI Algorithms for Classification","created":"2021-05-20","cited_by_count":8},{"id":"2302.05624","title":"A novel approach to generate datasets with XAI ground truth to evaluate image models","created":"2023-02-11","cited_by_count":4},{"id":"2308.03161","title":"Precise Benchmarking of Explainable AI Attribution Methods","created":"2023-08-06","cited_by_count":4},{"id":"2106.08376","title":"A Framework for Evaluating Post Hoc Feature-Additive Explainers","created":"2021-06-15","cited_by_count":3},{"id":"2305.09477","title":"Unjustified Sample Sizes and Generalizations in Explainable AI Research: Principles for More Inclusive User Studies","created":"2023-05-08","cited_by_count":1},{"id":"2307.06963","title":"Is Task-Agnostic Explainable AI a Myth?","created":"2023-07-13","cited_by_count":1}],"next_cursor":null}