{"total":68,"rows":[{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017,"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":"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":"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":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81,"area":"lr"},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"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":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"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":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43,"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":"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":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2405.20774","title":"Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems","created":"2024-05-27","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":"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":"2507.02778","title":"Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models","created":"2025-07-03","cited_by_count":20,"area":"lr"},{"id":"2402.11907","title":"Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation","created":"2024-02-19","cited_by_count":18,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"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":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"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":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"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":"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":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2510.09714","title":"All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language","created":"2025-10-10","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":"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":"2602.13274","title":"ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2601.03537","title":"STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2603.15661","title":"DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2602.01795","title":"RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse","created":"2026-02-02","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":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2406.19552","title":"Rethinking harmless refusals when fine-tuning foundation models","created":"2024-06-27","cited_by_count":1,"area":"lr"},{"id":"2501.01872","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","created":"2025-01-03","cited_by_count":1,"area":"lr"},{"id":"2511.08055","title":"MSCR: Exploring the Vulnerability of LLMs' Mathematical Reasoning Abilities Using Multi-Source Candidate Replacement","created":"2025-11-11","cited_by_count":1,"area":"lr"},{"id":"2511.14106","title":"Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT","created":"2025-11-18","cited_by_count":1,"area":"lr"},{"id":"2601.03416","title":"GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.16506","title":"SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2603.00696","title":"DRIV-EX: Counterfactual Explanations for Driving LLMs","created":"2026-02-28","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":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2409.16779","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","created":"2024-09-25","cited_by_count":0,"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":"2604.02954","title":"LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2606.11046","title":"Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.12731","title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2607.04645","title":"Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2607.08180","title":"Out of Sight: Compression-Aware Content Protection against Agentic Crawlers","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.17786","title":"Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.15673","title":"PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.13948","title":"Thought without systematicity? Evaluating reasoning models on rule induction tasks","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2609.21677","title":"GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.39146","title":"MADBench: Benchmarking the Security of Multi-Agent Debate","created":"2026-09-30","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"},{"id":"2610.16312","title":"Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18566","title":"Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}