{"total":85,"rows":[{"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,"area":null},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2107.08720","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","created":"2021-07-19","cited_by_count":82,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"area":null},{"id":"2305.04446","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","created":"2023-05-08","cited_by_count":46,"area":null},{"id":"2103.01664","title":"Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection","created":"2021-03-02","cited_by_count":45,"area":null},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2106.15896","title":"Whose Opinions Matter? Perspective-aware Models to Identify Opinions of Hate Speech Victims in Abusive Language Detection","created":"2021-06-30","cited_by_count":38,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25,"area":null},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"id":"2405.15145","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","created":"2024-05-24","cited_by_count":24,"area":null},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2402.11886","title":"The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth","created":"2024-02-19","cited_by_count":20,"area":null},{"id":"2301.12534","title":"Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive","created":"2023-01-29","cited_by_count":16,"area":null},{"id":"2102.03870","title":"\"Short is the Road that Leads from Fear to Hate\": Fear Speech in Indian WhatsApp Groups","created":"2021-02-07","cited_by_count":13,"area":null},{"id":"2410.02378","title":"Towards Comprehensive Detection of Chinese Harmful Memes","created":"2024-10-03","cited_by_count":13,"area":null},{"id":"2110.14839","title":"Hate Speech Classifiers Learn Human-Like Social Stereotypes","created":"2021-10-28","cited_by_count":12,"area":null},{"id":"2412.11691","title":"Multilingual and Explainable Text Detoxification with Parallel Corpora","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2111.03299","title":"Dataset of Fake News Detection and Fact Verification: A Survey","created":"2021-11-05","cited_by_count":11,"area":null},{"id":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2106.09775","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2403.02268","title":"Subjective $\\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2307.11519","title":"Multi-modal Hate Speech Detection using Machine Learning","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2204.01334","title":"Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers","created":"2022-04-04","cited_by_count":7,"area":null},{"id":"2305.13589","title":"BiasX: \"Thinking Slow\" in Toxic Content Moderation with Explanations of Implied Social Biases","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2410.15911","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2109.07346","title":"Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2111.10223","title":"Toxicity Detection can be Sensitive to the Conversational Context","created":"2021-11-19","cited_by_count":6,"area":null},{"id":"2210.07934","title":"Codes, Patterns and Shapes of Contemporary Online Antisemitism and Conspiracy Narratives -- an Annotation Guide and Labeled German-Language Dataset in the Context of COVID-19","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2308.10592","title":"BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2311.00203","title":"Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2105.14898","title":"Retweet communities reveal the main sources of hate speech","created":"2021-05-31","cited_by_count":5,"area":null},{"id":"2108.12601","title":"Mitigation of Diachronic Bias in Fake News Detection Dataset","created":"2021-08-28","cited_by_count":5,"area":null},{"id":"2110.07566","title":"Practical Benefits of Feature Feedback Under Distribution Shift","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2103.09050","title":"Hate, Obscenity, and Insults: Measuring the Exposure of Children to Inappropriate Comments in YouTube","created":"2021-03-03","cited_by_count":4,"area":null},{"id":"2103.17191","title":"Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability","created":"2021-03-31","cited_by_count":4,"area":null},{"id":"2106.01033","title":"Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text","created":"2021-06-02","cited_by_count":4,"area":null},{"id":"2111.10390","title":"The ComMA Dataset V0.2: Annotating Aggression and Bias in Multilingual Social Media Discourse","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2112.06642","title":"Unraveling Social Perceptions & Behaviors towards Migrants on Twitter","created":"2021-12-04","cited_by_count":4,"area":null},{"id":"2211.17046","title":"Rationale-Guided Few-Shot Classification to Detect Abusive Language","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2312.11344","title":"Muted: Multilingual Targeted Offensive Speech Identification and Visualization","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2406.08080","title":"AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2502.17710","title":"Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2111.00981","title":"Cross-lingual Hate Speech Detection using Transformer Models","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2201.11294","title":"Highly Generalizable Models for Multilingual Hate Speech Detection","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2307.05578","title":"Hate Speech Detection via Dual Contrastive Learning","created":"2023-07-10","cited_by_count":3,"area":null},{"id":"2506.00973","title":"XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2201.05922","title":"Addressing the Challenges of Cross-Lingual Hate Speech Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2302.02064","title":"Lived Experience Matters: Automatic Detection of Stigma on Social Media Toward People Who Use Substances","created":"2023-02-04","cited_by_count":2,"area":null},{"id":"2401.09244","title":"Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2405.20755","title":"Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2411.19017","title":"A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2506.11919","title":"Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Study","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2107.13592","title":"Detecting Abusive Albanian","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2201.11770","title":"Going Extreme: Comparative Analysis of Hate Speech in Parler and Gab","created":"2022-01-27","cited_by_count":1,"area":null},{"id":"2304.01890","title":"Sociocultural knowledge is needed for selection of shots in hate speech detection tasks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2306.09752","title":"Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2403.11108","title":"HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2406.12304","title":"COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2407.15736","title":"OMoS-QA: A Dataset for Cross-Lingual Extractive Question Answering in a German Migration Context","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2409.17130","title":"Assessing the Level of Toxicity Against Distinct Groups in Bangla Social Media Comments: A Comprehensive Investigation","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.05287","title":"Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.22435","title":"Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2106.13238","title":"Hate Speech Detection in Clubhouse","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2107.02024","title":"Statistical Analysis of Perspective Scores on Hate Speech Detection","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2309.04027","title":"TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models","created":"2023-09-07","cited_by_count":0,"area":null},{"id":"2311.10514","title":"When a Language Question Is at Stake. A Revisited Approach to Label Sensitive Content","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2405.11030","title":"The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2409.17467","title":"What is the social benefit of hate speech detection research? A Systematic Review","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2502.07101","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2506.16190","title":"Web(er) of Hate: A Survey on How Hate Speech Is Typed","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2509.14264","title":"Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2604.09625","title":"Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.13899","title":"Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detection","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.27313","title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.23095","title":"Definitional Sensitivity in Media Bias Detection: A Multi-Definition Dataset and Benchmark","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}