{"total":17,"rows":[{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2304.10619","title":"\"HOT\" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media","created":"2023-04-20","cited_by_count":45,"area":"safety"},{"id":"2212.10440","title":"Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data","created":"2022-12-20","cited_by_count":22,"area":"safety"},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16,"area":"safety"},{"id":"2312.07420","title":"FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs","created":"2023-12-12","cited_by_count":10,"area":"safety"},{"id":"2308.02080","title":"Causality Guided Disentanglement for Cross-Platform Hate Speech Detection","created":"2023-08-03","cited_by_count":9,"area":"safety"},{"id":"2505.14316","title":"Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion","created":"2025-05-20","cited_by_count":9,"area":"safety"},{"id":"2403.19836","title":"Target Span Detection for Implicit Harmful Content","created":"2024-03-28","cited_by_count":8,"area":"safety"},{"id":"2502.01241","title":"Peering Behind the Shield: Guardrail Identification in Large Language Models","created":"2025-02-03","cited_by_count":5,"area":"safety"},{"id":"2505.14524","title":"Guarded Query Routing for Large Language Models","created":"2025-05-20","cited_by_count":2,"area":"safety"},{"id":"2511.16689","title":"Concept-Based Interpretability for Toxicity Detection","created":"2025-11-15","cited_by_count":1,"area":"safety"},{"id":"2311.10236","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","created":"2023-11-16","cited_by_count":0,"area":"safety"},{"id":"2508.04166","title":"STEMTOX: From Collaborative Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning","created":"2025-08-06","cited_by_count":0,"area":"safety"},{"id":"2608.24191","title":"'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection","created":"2026-08-25","cited_by_count":0,"area":"safety"},{"id":"2608.25605","title":"From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2610.06503","title":"Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.18588","title":"Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}