{"list":"other","total":61,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"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":"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":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1803.05449","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","created":"2018-03-14","cited_by_count":294},{"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":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1907.07355","title":"Probing Neural Network Comprehension of Natural Language Arguments","created":"2019-07-17","cited_by_count":214},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"1710.11342","title":"Generating Natural Adversarial Examples","created":"2017-10-31","cited_by_count":183},{"id":"1908.07898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","created":"2019-08-21","cited_by_count":175},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","cited_by_count":159},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"1908.10763","title":"Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual","created":"2019-08-28","cited_by_count":119},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","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":"1808.09384","title":"What Makes Reading Comprehension Questions Easier?","created":"2018-08-28","cited_by_count":60},{"id":"1804.08117","title":"Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment","created":"2018-04-22","cited_by_count":59},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47},{"id":"1702.01841","title":"The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task","created":"2017-02-07","cited_by_count":39},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38},{"id":"1802.04302","title":"Evaluating Compositionality in Sentence Embeddings","created":"2018-02-12","cited_by_count":35},{"id":"2004.02709","title":"Evaluating Models' Local Decision Boundaries via Contrast Sets","created":"2020-04-06","cited_by_count":24},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23},{"id":"1903.08237","title":"When redundancy is useful: A Bayesian approach to 'overinformative' referring expressions","created":"2019-03-19","cited_by_count":21},{"id":"1805.11818","title":"Visual Referring Expression Recognition: What Do Systems Actually Learn?","created":"2018-05-30","cited_by_count":20},{"id":"1912.13337","title":"What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge","created":"2019-12-31","cited_by_count":19},{"id":"1805.01035","title":"Split and Rephrase: Better Evaluation and a Stronger Baseline","created":"2018-05-02","cited_by_count":15},{"id":"2007.06898","title":"Our Evaluation Metric Needs an Update to Encourage Generalization","created":"2020-07-14","cited_by_count":12},{"id":"1906.09635","title":"Investigating Biases in Textual Entailment Datasets","created":"2019-06-23","cited_by_count":4},{"id":"1806.03561","title":"What Knowledge is Needed to Solve the RTE5 Textual Entailment Challenge?","created":"2018-06-10","cited_by_count":2}],"next_cursor":null}