{"list":"other","total":121,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"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":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1706.07979","title":"Methods for Interpreting and Understanding Deep Neural Networks","created":"2017-06-24","cited_by_count":345},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2002.06673","title":"Performative Prediction","created":"2020-02-16","cited_by_count":327},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"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":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"1804.11192","title":"Explainable Recommendation: A Survey and New Perspectives","created":"2018-04-30","cited_by_count":210},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209},{"id":"1903.12394","title":"Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems","created":"2019-03-29","cited_by_count":205},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"1805.10820","title":"Local Rule-Based Explanations of Black Box Decision Systems","created":"2018-05-28","cited_by_count":166},{"id":"1905.06088","title":"Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning","created":"2019-05-15","cited_by_count":151},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"2001.05371","title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations","created":"2020-01-15","cited_by_count":142},{"id":"1805.03364","title":"A Symbolic Approach to Explaining Bayesian Network Classifiers","created":"2018-05-09","cited_by_count":131},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"2004.14545","title":"Explainable Deep Learning: A Field Guide for the Uninitiated","created":"2020-04-30","cited_by_count":127},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123},{"id":"2010.05607","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","created":"2020-10-12","cited_by_count":122},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"2105.04289","title":"Do Concept Bottleneck Models Learn as Intended?","created":"2021-05-10","cited_by_count":116},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"1912.05100","title":"Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches","created":"2019-12-11","cited_by_count":101},{"id":"2009.11698","title":"Principles and Practice of Explainable Machine Learning","created":"2020-09-18","cited_by_count":99},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"1912.09818","title":"When Explanations Lie: Why Many Modified BP Attributions Fail","created":"2019-12-20","cited_by_count":92},{"id":"2009.08634","title":"On the Tractability of SHAP Explanations","created":"2020-09-18","cited_by_count":92},{"id":"2001.03447","title":"Explaining the Explainer: A First Theoretical Analysis of LIME","created":"2020-01-10","cited_by_count":89},{"id":"2011.14340","title":"ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery","created":"2020-11-29","cited_by_count":89},{"id":"1807.05185","title":"Model Reconstruction from Model Explanations","created":"2018-07-13","cited_by_count":86},{"id":"1805.09901","title":"Boolean Decision Rules via Column Generation","created":"2018-05-24","cited_by_count":80},{"id":"1902.02302","title":"Neural Network Attributions: A Causal Perspective","created":"2019-02-06","cited_by_count":77},{"id":"1502.04269","title":"Supersparse Linear Integer Models for Optimized Medical Scoring Systems","created":"2015-02-15","cited_by_count":76},{"id":"1503.01161","title":"The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification","created":"2015-03-03","cited_by_count":76},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"1802.00682","title":"How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation","created":"2018-02-02","cited_by_count":72},{"id":"2007.09969","title":"Fairwashing Explanations with Off-Manifold Detergent","created":"2020-07-20","cited_by_count":72},{"id":"2103.12308","title":"IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography","created":"2021-03-23","cited_by_count":72},{"id":"1711.06178","title":"Beyond Sparsity: Tree Regularization of Deep Models for Interpretability","created":"2017-11-16","cited_by_count":68},{"id":"1806.05337","title":"Hierarchical interpretations for neural network predictions","created":"2018-06-14","cited_by_count":66},{"id":"1906.10651","title":"Interpretable Image Recognition with Hierarchical Prototypes","created":"2019-06-25","cited_by_count":65},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65},{"id":"2001.09734","title":"One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency","created":"2020-01-27","cited_by_count":64},{"id":"2105.05330","title":"Neuro-Symbolic Artificial Intelligence: Current Trends","created":"2021-05-11","cited_by_count":54},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52},{"id":"1704.01701","title":"Learning Certifiably Optimal Rule Lists for Categorical Data","created":"2017-04-06","cited_by_count":50},{"id":"2011.02863","title":"This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition","created":"2020-11-05","cited_by_count":50},{"id":"2010.11034","title":"On Explaining Decision Trees","created":"2020-10-21","cited_by_count":49},{"id":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49},{"id":"1810.10118","title":"Interpreting Black Box Predictions using Fisher Kernels","created":"2018-10-23","cited_by_count":48},{"id":"2101.07685","title":"GLocalX -- From Local to Global Explanations of Black Box AI Models","created":"2021-01-19","cited_by_count":48},{"id":"2006.14804","title":"Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation","created":"2020-06-26","cited_by_count":42},{"id":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41},{"id":"1710.08191","title":"Human-in-the-loop Artificial Intelligence","created":"2017-10-23","cited_by_count":40},{"id":"2010.04987","title":"FIND: Human-in-the-Loop Debugging Deep Text Classifiers","created":"2020-10-10","cited_by_count":40},{"id":"1408.5456","title":"Interpreting Tree Ensembles with inTrees","created":"2014-08-23","cited_by_count":37},{"id":"2009.10259","title":"ALICE: Active Learning with Contrastive Natural Language Explanations","created":"2020-09-22","cited_by_count":36},{"id":"2109.09904","title":"Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems","created":"2021-09-21","cited_by_count":36},{"id":"1902.06787","title":"Regularizing Black-box Models for Improved Interpretability","created":"2019-02-18","cited_by_count":35},{"id":"1905.03540","title":"Embedding Human Knowledge into Deep Neural Network via Attention Map","created":"2019-05-09","cited_by_count":33},{"id":"2007.11500","title":"Debiasing Concept-based Explanations with Causal Analysis","created":"2020-07-22","cited_by_count":32},{"id":"2201.09051","title":"On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations","created":"2022-01-22","cited_by_count":32},{"id":"1802.06924","title":"Teaching Categories to Human Learners with Visual Explanations","created":"2018-02-20","cited_by_count":30},{"id":"2006.16789","title":"Causality Learning: A New Perspective for Interpretable Machine Learning","created":"2020-06-27","cited_by_count":28},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24}],"next_cursor":"100"}