{"total":27,"rows":[{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"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":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"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":"2510.01995","title":"LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2410.15623","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","created":"2024-10-21","cited_by_count":5,"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":"2412.15268","title":"Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2503.07237","title":"LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2502.19612","title":"Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2511.07065","title":"Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2410.21695","title":"CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2508.20750","title":"Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.03683","title":"Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2603.02684","title":"HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.00323","title":"Large Language Models in the Abuse Detection Pipeline","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2504.12082","title":"Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2606.11953","title":"Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.15905","title":"CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.19006","title":"Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22018","title":"SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.27462","title":"Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.19778","title":"Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}