{"total":14,"rows":[{"id":"2408.11727","title":"Efficient Detection of Toxic Prompts in Large Language Models","created":"2024-08-21","cited_by_count":13,"area":null},{"id":"2411.01844","title":"DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship","created":"2024-11-04","cited_by_count":7,"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":"2506.06347","title":"Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2411.17876","title":"Leveraging Large Language Models and Topic Modeling for Toxicity Classification","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2505.11725","title":"CLT and Edgeworth Expansion for m-out-of-n Bootstrap Estimators of The Studentized Median","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.15255","title":"Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2510.19331","title":"Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2406.06574","title":"Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2505.12116","title":"A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings","created":"2025-05-17","cited_by_count":1,"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":"2601.09342","title":"Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.14843","title":"ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.24000","title":"Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities","created":"2026-05-18","cited_by_count":0,"area":null}],"next_cursor":null}