{"list":"other","total":82,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"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":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"1908.08474","title":"The many Shapley values for model explanation","created":"2019-08-22","cited_by_count":344},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"1802.03888","title":"Consistent Individualized Feature Attribution for Tree Ensembles","created":"2018-02-12","cited_by_count":285},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"1612.08468","title":"Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models","created":"2016-12-27","cited_by_count":213},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"1910.13413","title":"Feature relevance quantification in explainable AI: A causal problem","created":"2019-10-29","cited_by_count":167},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"1912.03277","title":"Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers","created":"2019-12-06","cited_by_count":144},{"id":"1511.01644","title":"Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model","created":"2015-11-05","cited_by_count":140},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"1511.08228","title":"Neural GPUs Learn Algorithms","created":"2015-11-25","cited_by_count":121},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"1602.08610","title":"Scalable Bayesian Rule Lists","created":"2016-02-27","cited_by_count":64},{"id":"1707.09168","title":"Learning to Predict Charges for Criminal Cases with Legal Basis","created":"2017-07-28","cited_by_count":61},{"id":"1711.09724","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","created":"2017-11-27","cited_by_count":54},{"id":"1805.04755","title":"A Simple and Effective Model-Based Variable Importance Measure","created":"2018-05-12","cited_by_count":51},{"id":"1905.03969","title":"Legal Judgment Prediction via Multi-Perspective Bi-Feedback Network","created":"2019-05-10","cited_by_count":50},{"id":"1705.08504","title":"Interpreting Blackbox Models via Model Extraction","created":"2017-05-23","cited_by_count":44},{"id":"1511.06392","title":"Neural Random-Access Machines","created":"2015-11-19","cited_by_count":34},{"id":"1910.12853","title":"A Game Theoretic Approach to Class-wise Selective Rationalization","created":"2019-10-28","cited_by_count":32},{"id":"1802.03788","title":"Influence-Directed Explanations for Deep Convolutional Networks","created":"2018-02-11","cited_by_count":31},{"id":"1910.00163","title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","created":"2019-10-01","cited_by_count":27},{"id":"2012.08884","title":"Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration","created":"2020-12-16","cited_by_count":25},{"id":"1802.05287","title":"What is Gab? A Bastion of Free Speech or an Alt-Right Echo Chamber?","created":"2018-02-14","cited_by_count":24},{"id":"1709.00155","title":"Order-Planning Neural Text Generation From Structured Data","created":"2017-09-01","cited_by_count":20},{"id":"1804.01955","title":"Explanations of model predictions with live and breakDown packages","created":"2018-04-05","cited_by_count":17},{"id":"1806.03000","title":"Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative","created":"2018-06-08","cited_by_count":11},{"id":"1807.03688","title":"Inside the Right-Leaning Echo Chambers: Characterizing Gab, an Unmoderated Social System","created":"2018-07-10","cited_by_count":10},{"id":"1809.01499","title":"Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts","created":"2018-09-01","cited_by_count":9},{"id":"2012.08883","title":"Multi-type Disentanglement without Adversarial Training","created":"2020-12-16","cited_by_count":6},{"id":"1805.06536","title":"Are BLEU and Meaning Representation in Opposition?","created":"2018-05-16","cited_by_count":5},{"id":"1807.08518","title":"Implementing Neural Turing Machines","created":"2018-07-23","cited_by_count":4}],"next_cursor":null}