{"list":"other","total":89,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"1906.04571","title":"Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology","created":"2019-06-11","cited_by_count":200},{"id":"1908.06083","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","created":"2019-08-17","cited_by_count":176},{"id":"2004.12651","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","created":"2020-04-27","cited_by_count":170},{"id":"1911.03842","title":"Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation","created":"2019-11-10","cited_by_count":152},{"id":"1706.02409","title":"A Convex Framework for Fair Regression","created":"2017-06-07","cited_by_count":148},{"id":"1911.03064","title":"Reducing Sentiment Bias in Language Models via Counterfactual Evaluation","created":"2019-11-08","cited_by_count":148},{"id":"2012.15859","title":"Intrinsic Bias Metrics Do Not Correlate with Application Bias","created":"2020-12-31","cited_by_count":148},{"id":"1906.08386","title":"Inherent Tradeoffs in Learning Fair Representations","created":"2019-06-19","cited_by_count":144},{"id":"1705.06476","title":"ParlAI: A Dialog Research Software Platform","created":"2017-05-18","cited_by_count":139},{"id":"2010.13561","title":"Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure","created":"2020-10-23","cited_by_count":138},{"id":"2004.04487","title":"Injecting Numerical Reasoning Skills into Language Models","created":"2020-04-09","cited_by_count":133},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"1804.09000","title":"Style Transfer Through Back-Translation","created":"2018-04-24","cited_by_count":124},{"id":"1809.02208","title":"Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate","created":"2018-09-06","cited_by_count":121},{"id":"1705.09899","title":"Understanding Abuse: A Typology of Abusive Language Detection Subtasks","created":"2017-05-28","cited_by_count":116},{"id":"2005.00683","title":"Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models","created":"2020-05-02","cited_by_count":110},{"id":"1909.00871","title":"It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution","created":"2019-09-02","cited_by_count":103},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2009.10195","title":"SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness","created":"2020-09-21","cited_by_count":96},{"id":"2005.00614","title":"Multi-Dimensional Gender Bias Classification","created":"2020-05-01","cited_by_count":80},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75},{"id":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","cited_by_count":75},{"id":"1910.04210","title":"Perturbation Sensitivity Analysis to Detect Unintended Model Biases","created":"2019-10-09","cited_by_count":74},{"id":"1909.02670","title":"In Plain Sight: Media Bias Through the Lens of Factual Reporting","created":"2019-09-05","cited_by_count":68},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68},{"id":"1805.05206","title":"DeepMutation: Mutation Testing of Deep Learning Systems","created":"2018-05-14","cited_by_count":67},{"id":"2010.13816","title":"PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction","created":"2020-10-26","cited_by_count":59},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53},{"id":"1505.05723","title":"On the relation between accuracy and fairness in binary classification","created":"2015-05-21","cited_by_count":48},{"id":"2202.11923","title":"Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender","created":"2022-02-24","cited_by_count":47},{"id":"2102.06788","title":"They, Them, Theirs: Rewriting with Gender-Neutral English","created":"2021-02-12","cited_by_count":44},{"id":"2201.06494","title":"AugLy: Data Augmentations for Robustness","created":"2022-01-17","cited_by_count":34},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30},{"id":"2109.05620","title":"RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models","created":"2021-09-12","cited_by_count":28},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23},{"id":"2111.04158","title":"A Word on Machine Ethics: A Response to Jiang et al. (2021)","created":"2021-11-07","cited_by_count":23},{"id":"2104.07838","title":"Investigating Failures of Automatic Translation in the Case of Unambiguous Gender","created":"2021-04-16","cited_by_count":20},{"id":"2112.07447","title":"Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models","created":"2021-12-14","cited_by_count":20},{"id":"2205.05770","title":"De-biasing \"bias\" measurement","created":"2022-05-11","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":"2108.02854","title":"GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena","created":"2021-08-05","cited_by_count":16},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16},{"id":"2205.04238","title":"Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection","created":"2022-05-09","cited_by_count":11},{"id":"2104.05232","title":"Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation","created":"2021-04-12","cited_by_count":9},{"id":"1909.03343","title":"Investigating Sports Commentator Bias within a Large Corpus of American Football Broadcasts","created":"2019-09-07","cited_by_count":8},{"id":"2103.01341","title":"What Are We Really Testing in Mutation Testing for Machine Learning? A Critical Reflection","created":"2021-03-01","cited_by_count":7},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5}],"next_cursor":null}