{"list":"other","total":54,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1604.04173","title":"Distribution-Free Predictive Inference For Regression","created":"2016-04-14","cited_by_count":668},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2006.14779","title":"Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance","created":"2020-06-26","cited_by_count":399},{"id":"1801.01489","title":"All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously","created":"2018-01-04","cited_by_count":373},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2001.02478","title":"Questioning the AI: Informing Design Practices for Explainable AI User Experiences","created":"2020-01-08","cited_by_count":253},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"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},{"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":"1811.01439","title":"Explaining Explanations in AI","created":"2018-11-04","cited_by_count":137},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125},{"id":"2101.04719","title":"Expanding Explainability: Towards Social Transparency in AI systems","created":"2021-01-12","cited_by_count":124},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123},{"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":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2007.04131","title":"General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models","created":"2020-07-08","cited_by_count":75},{"id":"2007.09969","title":"Fairwashing Explanations with Off-Manifold Detergent","created":"2020-07-20","cited_by_count":72},{"id":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59},{"id":"2201.10295","title":"Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts","created":"2022-01-25","cited_by_count":53},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52},{"id":"2011.06169","title":"Robust and Stable Black Box Explanations","created":"2020-11-12","cited_by_count":47},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42},{"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":"2112.09745","title":"Interpretable Data-Based Explanations for Fairness Debugging","created":"2021-12-17","cited_by_count":30},{"id":"2309.13775","title":"The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance","created":"2023-09-24","cited_by_count":29},{"id":"2010.13764","title":"Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability","created":"2020-10-26","cited_by_count":25},{"id":"2306.04292","title":"Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research","created":"2023-06-07","cited_by_count":22},{"id":"2305.03712","title":"Statistical Inference for Fairness Auditing","created":"2023-05-05","cited_by_count":20},{"id":"2007.01283","title":"Floodgate: inference for model-free variable importance","created":"2020-07-02","cited_by_count":16},{"id":"2111.10853","title":"Decorrelated Variable Importance","created":"2021-11-21","cited_by_count":13},{"id":"2301.04041","title":"Manifold Restricted Interventional Shapley Values","created":"2023-01-10","cited_by_count":9},{"id":"2310.01685","title":"A Framework for Interpretability in Machine Learning for Medical Imaging","created":"2023-10-02","cited_by_count":9},{"id":"2401.08513","title":"X Hacking: The Threat of Misguided AutoML","created":"2024-01-16","cited_by_count":5},{"id":"2310.10203","title":"Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes","created":"2023-10-16","cited_by_count":2},{"id":"2212.03131","title":"Explainability as statistical inference","created":"2022-12-06","cited_by_count":1}],"next_cursor":null}