{"list":"other","total":54,"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"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":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"1905.12516","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","created":"2019-05-29","cited_by_count":209},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"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":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"2004.01670","title":"Directions in Abusive Language Training Data: Garbage In, Garbage Out","created":"2020-04-03","cited_by_count":140},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"1905.08941","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","created":"2019-05-22","cited_by_count":125},{"id":"2006.00998","title":"Toxicity Detection: Does Context Really Matter?","created":"2020-06-01","cited_by_count":93},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2109.09193","title":"Towards Zero-Label Language Learning","created":"2021-09-19","cited_by_count":76},{"id":"2009.13818","title":"A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation","created":"2020-09-29","cited_by_count":72},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2004.14454","title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification","created":"2020-04-29","cited_by_count":53},{"id":"2004.06465","title":"Deep Learning Models for Multilingual Hate Speech Detection","created":"2020-04-14","cited_by_count":49},{"id":"1809.02255","title":"Adversarial Domain Adaptation for Duplicate Question Detection","created":"2018-09-07","cited_by_count":30},{"id":"2104.05232","title":"Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation","created":"2021-04-12","cited_by_count":9}],"next_cursor":null}