{"total":17,"rows":[{"id":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"id":"2604.18519","title":"LLM Safety From Within: Detecting Harmful Content with Internal Representations","created":"2026-04-20","cited_by_count":11,"area":"safety"},{"id":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","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":"2505.02009","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","created":"2025-05-04","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":"2506.12299","title":"QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2502.12464","title":"SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models","created":"2025-02-18","cited_by_count":3,"area":"safety"},{"id":"2510.18454","title":"Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models","created":"2025-10-21","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":"2502.05291","title":"Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet","created":"2025-02-07","cited_by_count":0,"area":"safety"},{"id":"2504.16120","title":"A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content","created":"2025-04-19","cited_by_count":0,"area":"safety"},{"id":"2605.29659","title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.05936","title":"Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2607.28187","title":"Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation","created":"2026-07-30","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":"2609.13737","title":"ForeSight: Enhancing Risk Monitoring via Early Safety Signal Distillation","created":"2026-09-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}