{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"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":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"1911.03343","title":"Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly","created":"2019-11-08","cited_by_count":243},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"1908.05803","title":"Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning","created":"2019-08-16","cited_by_count":100},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91},{"id":"1808.04926","title":"How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks","created":"2018-08-14","cited_by_count":88},{"id":"1906.02900","title":"Compositional Questions Do Not Necessitate Multi-hop Reasoning","created":"2019-06-07","cited_by_count":88},{"id":"2004.14602","title":"Look at the First Sentence: Position Bias in Question Answering","created":"2020-04-30","cited_by_count":84},{"id":"1606.02858","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","created":"2016-06-09","cited_by_count":72},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67},{"id":"1609.08667","title":"Deep Reinforcement Learning for Mention-Ranking Coreference Models","created":"2016-09-27","cited_by_count":63},{"id":"1808.09384","title":"What Makes Reading Comprehension Questions Easier?","created":"2018-08-28","cited_by_count":60},{"id":"2009.06354","title":"QED: A Framework and Dataset for Explanations in Question Answering","created":"2020-09-08","cited_by_count":55},{"id":"1904.12106","title":"Understanding Dataset Design Choices for Multi-hop Reasoning","created":"2019-04-27","cited_by_count":50},{"id":"2101.07685","title":"GLocalX -- From Local to Global Explanations of Black Box AI Models","created":"2021-01-19","cited_by_count":48},{"id":"1911.09241","title":"Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets","created":"2019-11-21","cited_by_count":46},{"id":"2004.03490","title":"What do Models Learn from Question Answering Datasets?","created":"2020-04-07","cited_by_count":45},{"id":"2104.12871","title":"Why AI is Harder Than We Think","created":"2021-04-26","cited_by_count":41},{"id":"2003.02249","title":"jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models","created":"2020-03-04","cited_by_count":39},{"id":"2005.01525","title":"To Test Machine Comprehension, Start by Defining Comprehension","created":"2020-05-04","cited_by_count":31},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20},{"id":"2109.07022","title":"How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?","created":"2021-09-14","cited_by_count":19},{"id":"2003.04642","title":"A Framework for Evaluation of Machine Reading Comprehension Gold Standards","created":"2020-03-10","cited_by_count":18},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11},{"id":"2012.15573","title":"Coreference Reasoning in Machine Reading Comprehension","created":"2020-12-31","cited_by_count":6},{"id":"1809.03740","title":"Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System","created":"2018-09-11","cited_by_count":3},{"id":"2109.07102","title":"Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?","created":"2021-09-15","cited_by_count":2}],"next_cursor":null}