{"list":"other","total":51,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1905.07697","title":"Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations","created":"2019-05-19","cited_by_count":614},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"1908.08474","title":"The many Shapley values for model explanation","created":"2019-08-22","cited_by_count":344},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"1910.13413","title":"Feature relevance quantification in explainable AI: A causal problem","created":"2019-10-29","cited_by_count":167},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1807.08024","title":"Explaining Image Classifiers by Counterfactual Generation","created":"2018-07-20","cited_by_count":144},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"1802.09596","title":"Tunability: Importance of Hyperparameters of Machine Learning Algorithms","created":"2018-02-26","cited_by_count":99},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"1806.08838","title":"Bayesian Optimization of Combinatorial Structures","created":"2018-06-22","cited_by_count":64},{"id":"1904.01606","title":"Inferring Which Medical Treatments Work from Reports of Clinical Trials","created":"2019-04-02","cited_by_count":64},{"id":"1710.04725","title":"Hyperparameter Importance Across Datasets","created":"2017-10-12","cited_by_count":63},{"id":"2004.14992","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","created":"2020-04-30","cited_by_count":63},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","cited_by_count":59},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"2010.13984","title":"Interpretation of NLP models through input marginalization","created":"2020-10-27","cited_by_count":44},{"id":"1902.06918","title":"Explaining a black-box using Deep Variational Information Bottleneck Approach","created":"2019-02-19","cited_by_count":36},{"id":"2010.00667","title":"Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers","created":"2020-10-01","cited_by_count":35},{"id":"1502.02127","title":"Hyperparameter Search in Machine Learning","created":"2015-02-07","cited_by_count":33},{"id":"1703.05667","title":"End-to-End Learning for Structured Prediction Energy Networks","created":"2017-03-16","cited_by_count":33},{"id":"2010.08973","title":"Feature Importance Ranking for Deep Learning","created":"2020-10-18","cited_by_count":31},{"id":"1904.11829","title":"Evaluating Recurrent Neural Network Explanations","created":"2019-04-26","cited_by_count":29},{"id":"2101.00905","title":"On Baselines for Local Feature Attributions","created":"2021-01-04","cited_by_count":29},{"id":"1908.06870","title":"Fine-grained Sentiment Analysis with Faithful Attention","created":"2019-08-19","cited_by_count":23},{"id":"1910.13503","title":"Weight of Evidence as a Basis for Human-Oriented Explanations","created":"2019-10-29","cited_by_count":10},{"id":"2009.11150","title":"Information-Theoretic Visual Explanation for Black-Box Classifiers","created":"2020-09-23","cited_by_count":3}],"next_cursor":null}