{"list":"other","total":64,"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"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":"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":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"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":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"1808.09031","title":"Targeted Syntactic Evaluation of Language Models","created":"2018-08-27","cited_by_count":242},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"1908.05267","title":"Towards Debiasing Fact Verification Models","created":"2019-08-14","cited_by_count":143},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"1908.10763","title":"Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual","created":"2019-08-28","cited_by_count":119},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"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":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2004.03066","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","created":"2020-04-07","cited_by_count":77},{"id":"2005.00636","title":"We Need to Talk About Random Splits","created":"2020-05-01","cited_by_count":71},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56},{"id":"2102.01335","title":"Neural Data Augmentation via Example Extrapolation","created":"2021-02-02","cited_by_count":54},{"id":"1904.02668","title":"Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets","created":"2019-04-04","cited_by_count":42},{"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":"1704.07431","title":"A Challenge Set Approach to Evaluating Machine Translation","created":"2017-04-24","cited_by_count":37},{"id":"2010.08580","title":"Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets","created":"2020-10-16","cited_by_count":31},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","cited_by_count":30},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23},{"id":"2010.03656","title":"Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data","created":"2020-10-07","cited_by_count":20},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9}],"next_cursor":null}