{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1610.07524","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","created":"2016-10-24","cited_by_count":672},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"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":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"1703.09207","title":"Fairness in Criminal Justice Risk Assessments: The State of the Art","created":"2017-03-27","cited_by_count":315},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"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":"1802.00393","title":"Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior","created":"2018-02-01","cited_by_count":270},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"1905.12516","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","created":"2019-05-29","cited_by_count":209},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"2007.08100","title":"Towards Debiasing Sentence Representations","created":"2020-07-16","cited_by_count":171},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"1908.05267","title":"Towards Debiasing Fact Verification Models","created":"2019-08-14","cited_by_count":143},{"id":"2112.01640","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","created":"2021-12-02","cited_by_count":143},{"id":"1912.11078","title":"Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview","created":"2019-11-09","cited_by_count":137},{"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":"1701.08118","title":"Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis","created":"2017-01-27","cited_by_count":96},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96},{"id":"2008.06460","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","created":"2020-08-14","cited_by_count":87},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86},{"id":"2005.02439","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2020-05-05","cited_by_count":84},{"id":"2110.00413","title":"Detecting Harmful Memes and Their Targets","created":"2021-09-24","cited_by_count":78},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66},{"id":"2005.12246","title":"Demoting Racial Bias in Hate Speech Detection","created":"2020-05-25","cited_by_count":62},{"id":"1812.01693","title":"Spread of hate speech in online social media","created":"2018-12-04","cited_by_count":59},{"id":"2002.10361","title":"Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition","created":"2020-02-24","cited_by_count":43},{"id":"2004.14088","title":"Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting","created":"2020-04-29","cited_by_count":41},{"id":"2001.05495","title":"Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations","created":"2020-01-15","cited_by_count":40},{"id":"2110.11010","title":"Algorithmic Amplification of Politics on Twitter","created":"2021-10-21","cited_by_count":38},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31},{"id":"1804.03124","title":"Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection","created":"2018-04-09","cited_by_count":25},{"id":"2103.03417","title":"Measuring Model Biases in the Absence of Ground Truth","created":"2021-03-05","cited_by_count":24},{"id":"2005.05921","title":"Intersectional Bias in Hate Speech and Abusive Language Datasets","created":"2020-05-12","cited_by_count":22},{"id":"2105.02778","title":"The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification","created":"2021-05-06","cited_by_count":18},{"id":"2010.04377","title":"Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter","created":"2020-10-09","cited_by_count":16},{"id":"1909.00453","title":"Topics to Avoid: Demoting Latent Confounds in Text Classification","created":"2019-09-01","cited_by_count":14},{"id":"2106.02821","title":"Lifelong Learning of Hate Speech Classification on Social Media","created":"2021-06-05","cited_by_count":14},{"id":"2109.02941","title":"Countering Online Hate Speech: An NLP Perspective","created":"2021-09-07","cited_by_count":12},{"id":"2106.09775","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","created":"2021-06-17","cited_by_count":9},{"id":"2107.12866","title":"Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach","created":"2021-07-27","cited_by_count":6},{"id":"1903.02088","title":"Limitations of Pinned AUC for Measuring Unintended Bias","created":"2019-03-05","cited_by_count":4},{"id":"1906.09635","title":"Investigating Biases in Textual Entailment Datasets","created":"2019-06-23","cited_by_count":4},{"id":"2005.13041","title":"Examining Racial Bias in an Online Abuse Corpus with Structural Topic Modeling","created":"2020-05-26","cited_by_count":3},{"id":"2201.00961","title":"Nipping in the Bud: Detection, Diffusion and Mitigation of Hate Speech on Social Media","created":"2022-01-04","cited_by_count":2}],"next_cursor":null}