{"total":24,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91,"area":"lr"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2501.17749","title":"Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation","created":"2025-01-29","cited_by_count":13,"area":"lr"},{"id":"2501.19180","title":"Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning","created":"2025-01-31","cited_by_count":11,"area":"lr"},{"id":"2508.00324","title":"R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge","created":"2025-08-01","cited_by_count":6,"area":"lr"},{"id":"2510.21285","title":"When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models","created":"2025-10-24","cited_by_count":6,"area":"lr"},{"id":"2508.04204","title":"ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments","created":"2025-08-06","cited_by_count":4,"area":"lr"},{"id":"2602.01600","title":"Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2507.03167","title":"Where Do Reasoning Models Refuse?","created":"2025-07-03","cited_by_count":3,"area":"lr"},{"id":"2505.13008","title":"Adversarial Reasoning for Repair Based on Inferred Program Intent","created":"2025-05-19","cited_by_count":2,"area":"lr"},{"id":"2507.15974","title":"Does More Inference-Time Compute Really Help Robustness?","created":"2025-07-21","cited_by_count":2,"area":"lr"},{"id":"2602.21346","title":"Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2602.04224","title":"RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}