{"total":17,"rows":[{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2406.12354","title":"Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models","created":"2024-06-18","cited_by_count":20,"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":"2601.06675","title":"Evaluating Cross-Lingual Unlearning in Multilingual Language Models","created":"2026-01-10","cited_by_count":3,"area":"safety"},{"id":"2507.05980","title":"Lost in Localization: Building RabakBench with Human-in-the-Loop Validation to Measure Multilingual Safety Gaps","created":"2025-07-08","cited_by_count":2,"area":"safety"},{"id":"2509.15260","title":"Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages","created":"2025-09-18","cited_by_count":2,"area":"safety"},{"id":"2512.02711","title":"CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer","created":"2025-12-02","cited_by_count":2,"area":"safety"},{"id":"2606.03291","title":"Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility","created":"2026-06-02","cited_by_count":2,"area":"safety"},{"id":"2410.24049","title":"Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs","created":"2024-10-31","cited_by_count":1,"area":"safety"},{"id":"2509.07768","title":"Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning","created":"2025-09-09","cited_by_count":1,"area":"safety"},{"id":"2604.05318","title":"DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects","created":"2026-04-07","cited_by_count":1,"area":"safety"},{"id":"2608.11146","title":"The Illusion of Cross-Lingual Safety in Low-Resource Languages","created":"2026-08-11","cited_by_count":1,"area":"safety"},{"id":"2503.18117","title":"Detection of Somali-written Fake News and Toxic Messages on the Social Media Using Transformer-based Language Models","created":"2025-03-23","cited_by_count":0,"area":"safety"},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2609.02177","title":"WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading","created":"2026-09-02","cited_by_count":0,"area":"safety"},{"id":"2610.06093","title":"Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII","created":"2026-10-05","cited_by_count":0,"area":"safety"}],"next_cursor":null}