{"total":225,"rows":[{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017,"area":"lr"},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573,"area":"lr"},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"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":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108,"area":"lr"},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"area":"lr"},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"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":"2506.00641","title":"AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents","created":"2025-05-31","cited_by_count":90,"area":"lr"},{"id":"2405.20978","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","created":"2024-05-31","cited_by_count":89,"area":"lr"},{"id":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81,"area":"lr"},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"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":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2502.11054","title":"Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-02-16","cited_by_count":64,"area":"lr"},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"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":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"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":"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":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","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":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"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":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33,"area":"lr"},{"id":"2402.10601","title":"When \"Competency\" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers","created":"2024-02-16","cited_by_count":30,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"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":"2402.14899","title":"Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image","created":"2024-02-22","cited_by_count":26,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"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":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"id":"2503.01781","title":"Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models","created":"2025-03-03","cited_by_count":23,"area":"lr"},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2512.07086","title":"ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking","created":"2025-12-08","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":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2503.01908","title":"UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning","created":"2025-02-28","cited_by_count":21,"area":"lr"},{"id":"2502.09673","title":"Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning","created":"2025-02-13","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":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19,"area":"lr"},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2505.15404","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","created":"2025-05-21","cited_by_count":18,"area":"lr"},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2402.13459","title":"Learning to Poison Large Language Models for Downstream Manipulation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2510.26418","title":"Chain-of-Thought Hijacking","created":"2025-10-30","cited_by_count":16,"area":"lr"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"id":"2410.21411","title":"SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization","created":"2024-10-28","cited_by_count":14,"area":"lr"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"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":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","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":"2508.04039","title":"Large Reasoning Models Are Autonomous Jailbreak Agents","created":"2025-08-04","cited_by_count":13,"area":"lr"},{"id":"2510.00938","title":"Large Reasoning Models Learn Better Alignment from Flawed Thinking","created":"2025-10-01","cited_by_count":13,"area":"lr"},{"id":"2412.09722","title":"GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers","created":"2024-12-12","cited_by_count":12,"area":"lr"},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"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":"2508.19277","title":"POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2605.11039","title":"The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck","created":"2026-05-11","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":"2501.14693","title":"Rethinking Table Instruction Tuning","created":"2025-01-24","cited_by_count":10,"area":"lr"},{"id":"2503.19134","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2504.16489","title":"Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate","created":"2025-04-23","cited_by_count":10,"area":"lr"},{"id":"2509.24967","title":"SecInfer: Preventing Prompt Injection via Inference-time Scaling","created":"2025-09-29","cited_by_count":10,"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":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2603.06621","title":"Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models","created":"2026-02-20","cited_by_count":9,"area":"lr"},{"id":"2407.16205","title":"Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models","created":"2024-07-23","cited_by_count":8,"area":"lr"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"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":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2505.16785","title":"CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2506.00668","title":"SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues","created":"2025-05-31","cited_by_count":7,"area":"lr"},{"id":"2506.13726","title":"Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models","created":"2025-06-16","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":"2512.10931","title":"Asynchronous Reasoning: Training-Free Interactive Thinking LLMs","created":"2025-12-11","cited_by_count":7,"area":"lr"},{"id":"2601.19202","title":"Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs","created":"2026-01-27","cited_by_count":7,"area":"lr"},{"id":"2505.16446","title":"Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2508.20737","title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","created":"2025-08-28","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":"2510.10013","title":"Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety","created":"2025-10-11","cited_by_count":5,"area":"lr"},{"id":"2510.11570","title":"Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2510.13190","title":"SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2510.26037","title":"SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning","created":"2025-10-30","cited_by_count":5,"area":"lr"}],"next_cursor":"100"}