{"total":48,"rows":[{"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":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"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,"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":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","cited_by_count":23,"area":null},{"id":"2504.14904","title":"VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform","created":"2025-04-21","cited_by_count":21,"area":null},{"id":"2301.11219","title":"Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?","created":"2023-01-26","cited_by_count":14,"area":null},{"id":"2401.06526","title":"MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection","created":"2024-01-12","cited_by_count":14,"area":null},{"id":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2109.10255","title":"Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language","created":"2021-09-21","cited_by_count":12,"area":null},{"id":"2101.11956","title":"Us vs. Them: A Dataset of Populist Attitudes, News Bias and Emotions","created":"2021-01-28","cited_by_count":9,"area":null},{"id":"2501.15451","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2109.13711","title":"One to rule them all: Towards Joint Indic Language Hate Speech Detection","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2306.01105","title":"Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2405.08562","title":"The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2412.13698","title":"Towards Efficient and Explainable Hate Speech Detection via Model Distillation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2402.08764","title":"A Dataset for the Detection of Dehumanizing Language","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2111.04951","title":"American Hate Crime Trends Prediction with Event Extraction","created":"2021-11-09","cited_by_count":2,"area":null},{"id":"2208.13595","title":"Combating high variance in Data-Scarce Implicit Hate Speech Classification","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2209.08697","title":"Quantifying How Hateful Communities Radicalize Online Users","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2309.11896","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2504.19594","title":"Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2506.03009","title":"Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.03458","title":"Culture Matters in Toxic Language Detection in Persian","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.11292","title":"Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2102.04521","title":"A study of text representations in Hate Speech Detection","created":"2021-02-08","cited_by_count":1,"area":null},{"id":"2108.10724","title":"How Hateful are Movies? A Study and Prediction on Movie Subtitles","created":"2021-08-19","cited_by_count":1,"area":null},{"id":"2110.12780","title":"Battling Hateful Content in Indic Languages HASOC '21","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2205.13164","title":"Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2305.01050","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","created":"2023-05-01","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":"2407.12471","title":"Characterization of Political Polarized Users Attacked by Language Toxicity on Twitter","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2104.04770","title":"UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models","created":"2021-04-10","cited_by_count":0,"area":null},{"id":"2105.11412","title":"Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2021-05-24","cited_by_count":0,"area":null},{"id":"2202.00540","title":"Dominant Set-based Active Learning for Text Classification and its Application to Online Social Media","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2204.13400","title":"Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2208.10898","title":"Don't Take it Personally: Analyzing Gender and Age Differences in Ratings of Online Humor","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2303.14475","title":"Informed Machine Learning, Centrality, CNN, Relevant Document Detection, Repatriation of Indigenous Human Remains","created":"2023-03-25","cited_by_count":0,"area":null},{"id":"2304.13568","title":"Toxic comments reduce the activity of volunteer editors on Wikipedia","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2410.08053","title":"A Target-Aware Analysis of Data Augmentation for Hate Speech Detection","created":"2024-10-10","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":"2510.20782","title":"A Use-Case Specific Dataset for Measuring Dimensions of Responsible Performance in LLM-generated Text","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.01350","title":"FC-CONAN: An Exhaustively Paired Dataset for Robust Evaluation of Retrieval Systems","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2609.20808","title":"Unifying Models of Intergroup Hostility in Online Discourse","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}