{"total":67,"rows":[{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"area":"lr"},{"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":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136,"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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"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":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"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":"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":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"area":"lr"},{"id":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41,"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":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","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":"2502.12202","title":"To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models","created":"2025-02-16","cited_by_count":22,"area":"lr"},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20,"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":"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":"2506.02873","title":"It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics","created":"2025-06-03","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":"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":"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":"2605.15239","title":"Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2405.00557","title":"Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment","created":"2024-05-01","cited_by_count":10,"area":"lr"},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2507.21652","title":"UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2509.17938","title":"D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models","created":"2025-09-22","cited_by_count":7,"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":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","cited_by_count":6,"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":"2504.02725","title":"SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning","created":"2025-04-03","cited_by_count":4,"area":"lr"},{"id":"2509.24269","title":"AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2505.21784","title":"Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2507.03167","title":"Where Do Reasoning Models Refuse?","created":"2025-07-03","cited_by_count":3,"area":"lr"},{"id":"2510.12063","title":"ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization","created":"2025-10-14","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":"2605.08930","title":"Internalizing Safety Understanding in Large Reasoning Models via Verification","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2602.10148","title":"Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks","created":"2026-02-09","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":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2509.18382","title":"Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2509.19775","title":"bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs","created":"2025-09-24","cited_by_count":1,"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":"2510.17759","title":"VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2510.18154","title":"Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2604.09665","title":"Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.18946","title":"Reasoning Structure Matters for Safety Alignment of Reasoning Models","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.08936","title":"Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories","created":"2026-05-09","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":"2511.21214","title":"Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2601.01624","title":"How Does Prefix Matter in Reasoning Model Tuning?","created":"2026-01-04","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":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.28467","title":"Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2607.20448","title":"Domyn-Small: A European 10B Reasoning Language Model","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2607.27594","title":"Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.09542","title":"Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.18471","title":"First Token Matters: Understanding Safety Collapse in Large Reasoning Models","created":"2026-09-16","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}