{"total":23,"rows":[{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"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":"2606.28725","title":"DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2501.01256","title":"Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2505.18927","title":"Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2504.08609","title":"A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English","created":"2025-04-11","cited_by_count":2,"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":"2501.05482","title":"HP-BERT: A framework for longitudinal study of Hinduphobia on social media via language models","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2504.15439","title":"Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2502.20837","title":"Tuning-Free Structured Sparse PCA via Deep Unfolding Networks","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.13251","title":"Stronger Together: Unleashing the Social Impact of Hate Speech Research","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.16847","title":"Understanding and Analyzing Inappropriately Targeting Language in Online Discourse: A Comparative Annotation Study","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.07216","title":"Bias-Aware Mislabeling Detection via Decoupled Confident Learning","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2507.10177","title":"Detoxify: A framework for abusive text transformation using LLMs","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.20614","title":"Before the Outrage: Challenges and Advances in Predicting Online Antisocial Behavior","created":"2025-07-28","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":"2601.02697","title":"Boosting Accuracy and Interpretability in Multilingual Hate Speech Detection Through Layer Freezing and Explainable AI","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.04654","title":"LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2602.08085","title":"Large language models for spreading dynamics in complex systems","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.15600","title":"The geometry of online conversations and the causal antecedents of conflictual discourse","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2607.00143","title":"Hate Speech Detection in Turkish and Arabic: A Comprehensive Study","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2610.15795","title":"An Explainable System for Offensive Content Detection in Nastaliq Urdu: Corpus Curation, Transformer Benchmarking, and Word-Level Attribution","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}