{"list":"other","total":89,"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"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":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"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":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"1808.07036","title":"QuAC : Question Answering in Context","created":"2018-08-21","cited_by_count":381},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","cited_by_count":156},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"1908.05267","title":"Towards Debiasing Fact Verification Models","created":"2019-08-14","cited_by_count":143},{"id":"2008.02637","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","created":"2020-08-06","cited_by_count":138},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"1906.02916","title":"Multi-hop Reading Comprehension through Question Decomposition and Rescoring","created":"2019-06-07","cited_by_count":119},{"id":"2002.09758","title":"Unsupervised Question Decomposition for Question Answering","created":"2020-02-22","cited_by_count":118},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2004.08994","title":"Adversarial Training for Large Neural Language Models","created":"2020-04-20","cited_by_count":111},{"id":"1511.02301","title":"The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations","created":"2015-11-07","cited_by_count":108},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"2004.14444","title":"The Effect of Natural Distribution Shift on Question Answering Models","created":"2020-04-29","cited_by_count":104},{"id":"2010.02329","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","created":"2020-10-05","cited_by_count":92},{"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":"2004.14174","title":"Reevaluating Adversarial Examples in Natural Language","created":"2020-04-25","cited_by_count":85},{"id":"2005.00315","title":"Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance","created":"2020-05-01","cited_by_count":85},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2004.14602","title":"Look at the First Sentence: Position Bias in Question Answering","created":"2020-04-30","cited_by_count":84},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76},{"id":"1906.07132","title":"Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA","created":"2019-06-17","cited_by_count":63},{"id":"1808.09384","title":"What Makes Reading Comprehension Questions Easier?","created":"2018-08-28","cited_by_count":60},{"id":"1904.12106","title":"Understanding Dataset Design Choices for Multi-hop Reasoning","created":"2019-04-27","cited_by_count":50},{"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":"1804.06473","title":"Robust Machine Comprehension Models via Adversarial Training","created":"2018-04-17","cited_by_count":44},{"id":"1904.02668","title":"Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets","created":"2019-04-04","cited_by_count":42},{"id":"2001.01582","title":"A Survey on Machine Reading Comprehension Systems","created":"2020-01-06","cited_by_count":41},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40},{"id":"1910.04601","title":"R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason","created":"2019-10-10","cited_by_count":36},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36},{"id":"2110.13472","title":"Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable","created":"2021-10-26","cited_by_count":35},{"id":"2005.01525","title":"To Test Machine Comprehension, Start by Defining Comprehension","created":"2020-05-04","cited_by_count":31},{"id":"1803.05223","title":"MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge","created":"2018-03-14","cited_by_count":30},{"id":"1910.12391","title":"What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?","created":"2019-10-28","cited_by_count":30},{"id":"2002.09919","title":"Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?","created":"2020-02-23","cited_by_count":30},{"id":"2105.11136","title":"Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models","created":"2021-05-24","cited_by_count":29},{"id":"1608.05457","title":"Who did What: A Large-Scale Person-Centered Cloze Dataset","created":"2016-08-19","cited_by_count":24},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24},{"id":"1905.09531","title":"MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants","created":"2019-05-23","cited_by_count":20},{"id":"2003.04642","title":"A Framework for Evaluation of Machine Reading Comprehension Gold Standards","created":"2020-03-10","cited_by_count":18},{"id":"2004.14004","title":"Benchmarking Robustness of Machine Reading Comprehension Models","created":"2020-04-29","cited_by_count":18},{"id":"2012.04056","title":"Semantics Altering Modifications for Evaluating Comprehension in Machine Reading","created":"2020-12-07","cited_by_count":13},{"id":"2107.03242","title":"Robustifying Multi-hop QA through Pseudo-Evidentiality Training","created":"2021-07-07","cited_by_count":13},{"id":"2010.03338","title":"Improving QA Generalization by Concurrent Modeling of Multiple Biases","created":"2020-10-07","cited_by_count":12},{"id":"2005.14709","title":"Beyond Leaderboards: A survey of methods for revealing weaknesses in Natural Language Inference data and models","created":"2020-05-29","cited_by_count":11},{"id":"2107.13935","title":"Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition","created":"2021-07-29","cited_by_count":11},{"id":"2109.08207","title":"Numerical reasoning in machine reading comprehension tasks: are we there yet?","created":"2021-09-16","cited_by_count":9},{"id":"2109.12264","title":"More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering","created":"2021-09-25","cited_by_count":8},{"id":"1812.02205","title":"Are you tough enough? Framework for Robustness Validation of Machine Comprehension Systems","created":"2018-12-05","cited_by_count":3}],"next_cursor":null}