{"list":"other","total":55,"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"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":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"2009.03393","title":"Generative Language Modeling for Automated Theorem Proving","created":"2020-09-07","cited_by_count":388},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"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":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"1909.01380","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","created":"2019-09-03","cited_by_count":139},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"1904.03396","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","created":"2019-04-06","cited_by_count":75},{"id":"1909.06639","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","created":"2019-09-14","cited_by_count":68},{"id":"1707.01943","title":"A causal framework for explaining the predictions of black-box sequence-to-sequence models","created":"2017-07-06","cited_by_count":58},{"id":"1612.07843","title":"\"What is Relevant in a Text Document?\": An Interpretable Machine Learning Approach","created":"2016-12-23","cited_by_count":53},{"id":"2002.00737","title":"Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction","created":"2020-01-30","cited_by_count":47},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37},{"id":"1812.09359","title":"NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks","created":"2018-12-21","cited_by_count":31},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30},{"id":"2204.12130","title":"LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models","created":"2022-04-26","cited_by_count":28},{"id":"2204.04636","title":"\"That Is a Suspicious Reaction!\": Interpreting Logits Variation to Detect NLP Adversarial Attacks","created":"2022-04-10","cited_by_count":24},{"id":"1907.03324","title":"A Human-Grounded Evaluation of SHAP for Alert Processing","created":"2019-07-07","cited_by_count":23},{"id":"2005.00806","title":"Teaching Machine Comprehension with Compositional Explanations","created":"2020-05-02","cited_by_count":22},{"id":"1801.05075","title":"A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learning","created":"2018-01-16","cited_by_count":21},{"id":"2203.08452","title":"Can Pre-trained Language Models Interpret Similes as Smart as Human?","created":"2022-03-16","cited_by_count":13},{"id":"2108.11574","title":"Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models","created":"2021-08-26","cited_by_count":5},{"id":"2108.13140","title":"DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation","created":"2021-08-30","cited_by_count":5},{"id":"2009.07494","title":"Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability","created":"2020-09-16","cited_by_count":3}],"next_cursor":null}