{"total":37,"rows":[{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"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":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"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":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"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":"2505.11063","title":"Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2510.08731","title":"When to Reason: Semantic Router for vLLM","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2508.16347","title":"Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs","created":"2025-08-22","cited_by_count":11,"area":"lr"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2506.04575","title":"Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?","created":"2025-06-05","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2509.23291","title":"Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces","created":"2025-09-27","cited_by_count":4,"area":"lr"},{"id":"2507.21540","title":"PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking","created":"2025-07-29","cited_by_count":3,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2602.02136","title":"Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"area":"lr"},{"id":"2512.10687","title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2602.13562","title":"Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.00012","title":"Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2509.23882","title":"Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B","created":"2025-09-28","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","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":"2603.21697","title":"Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2605.26772","title":"Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2610.16312","title":"Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}