{"list":"other","total":52,"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":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1802.00393","title":"Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior","created":"2018-02-01","cited_by_count":270},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"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":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150},{"id":"2004.01670","title":"Directions in Abusive Language Training Data: Garbage In, Garbage Out","created":"2020-04-03","cited_by_count":140},{"id":"1908.11049","title":"Multilingual and Multi-Aspect Hate Speech Analysis","created":"2019-08-29","cited_by_count":133},{"id":"1909.04251","title":"A Benchmark Dataset for Learning to Intervene in Online Hate Speech","created":"2019-09-10","cited_by_count":129},{"id":"1910.03270","title":"CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech","created":"2019-10-08","cited_by_count":110},{"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":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93},{"id":"1710.07395","title":"Detecting Online Hate Speech Using Context Aware Models","created":"2017-10-20","cited_by_count":72},{"id":"2009.10277","title":"Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning","created":"2020-09-22","cited_by_count":68},{"id":"2006.08328","title":"ETHOS: an Online Hate Speech Detection Dataset","created":"2020-06-11","cited_by_count":66},{"id":"1804.04257","title":"Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media","created":"2018-04-11","cited_by_count":59},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50},{"id":"2004.12764","title":"\"Call me sexist, but...\": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples","created":"2020-04-27","cited_by_count":48},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48},{"id":"2010.04543","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","created":"2020-10-09","cited_by_count":45},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","cited_by_count":41},{"id":"2005.03909","title":"Detecting East Asian Prejudice on Social Media","created":"2020-05-08","cited_by_count":40},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31},{"id":"1804.04649","title":"Peer to Peer Hate: Hate Speech Instigators and Their Targets","created":"2018-04-12","cited_by_count":30},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27},{"id":"2403.05696","title":"SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes","created":"2024-03-08","cited_by_count":24},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22},{"id":"2010.07414","title":"On Cross-Dataset Generalization in Automatic Detection of Online Abuse","created":"2020-10-14","cited_by_count":20},{"id":"1812.10400","title":"Detecting weak and strong Islamophobic hate speech on social media","created":"2018-12-12","cited_by_count":15},{"id":"2103.10195","title":"Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language","created":"2021-03-18","cited_by_count":15},{"id":"2201.06723","title":"Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech","created":"2022-01-18","cited_by_count":14},{"id":"2203.08565","title":"Geographic Adaptation of Pretrained Language Models","created":"2022-03-16","cited_by_count":14},{"id":"2301.11429","title":"Just Another Day on Twitter: A Complete 24 Hours of Twitter Data","created":"2023-01-26","cited_by_count":14},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13},{"id":"2211.15262","title":"HERDPhobia: A Dataset for Hate Speech against Fulani in Nigeria","created":"2022-11-28","cited_by_count":12},{"id":"1308.0683","title":"Where in the World are You? Geolocation and Language Identification in Twitter","created":"2013-08-03","cited_by_count":11},{"id":"1802.09416","title":"A Quality Type-aware Annotated Corpus and Lexicon for Harassment Research","created":"2018-02-26","cited_by_count":11},{"id":"2011.10280","title":"Are Chess Discussions Racist? An Adversarial Hate Speech Data Set","created":"2020-11-20","cited_by_count":10},{"id":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10},{"id":"1708.04358","title":"Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks","created":"2017-08-14","cited_by_count":8},{"id":"2110.10319","title":"LMSOC: An Approach for Socially Sensitive Pretraining","created":"2021-10-20","cited_by_count":8},{"id":"2002.11645","title":"Facebook Ads as a Demographic Tool to Measure the Urban-Rural Divide","created":"2020-02-26","cited_by_count":3},{"id":"2312.17704","title":"TuPy-E: detecting hate speech in Brazilian Portuguese social media with a novel dataset and comprehensive analysis of models","created":"2023-12-29","cited_by_count":3},{"id":"2403.07531","title":"How Language, Culture, and Geography shape Online Dialogue: Insights from Koo","created":"2024-03-12","cited_by_count":1}],"next_cursor":null}