{"total":23,"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":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2601.15588","title":"YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models","created":"2026-01-22","cited_by_count":19,"area":"lr"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"id":"2506.07736","title":"RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards","created":"2025-06-09","cited_by_count":14,"area":"lr"},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2602.04649","title":"Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models","created":"2026-02-04","cited_by_count":11,"area":"lr"},{"id":"2505.19690","title":"Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2504.02725","title":"SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning","created":"2025-04-03","cited_by_count":4,"area":"lr"},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2509.22250","title":"Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2506.07031","title":"HauntAttack: When Attack Follows Reasoning as a Shadow","created":"2025-06-08","cited_by_count":1,"area":"lr"},{"id":"2509.12936","title":"Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety","created":"2025-09-16","cited_by_count":1,"area":"lr"},{"id":"2605.29068","title":"Robust and Efficient Guardrails with Latent Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2508.12897","title":"RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2512.14100","title":"A First-Order Logic-Based Alternative to Reward Models in RLHF","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2606.16808","title":"Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2609.05910","title":"UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms","created":"2026-09-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}