{"total":25,"rows":[{"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":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257,"area":"lr"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81,"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":"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":"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":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"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":"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":"2503.17882","title":"Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2410.03122","title":"RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning","created":"2024-10-04","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":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2505.17106","title":"RRTL: Red Teaming Reasoning Large Language Models in Tool Learning","created":"2025-05-21","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":"2604.09750","title":"Conflicts Make Large Reasoning Models Vulnerable to Attacks","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2607.15286","title":"Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior","created":"2026-06-18","cited_by_count":1,"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":"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":"2609.23587","title":"On the Efficiency-Safety Dilemma in Large Reasoning Models","created":"2026-09-20","cited_by_count":0,"area":"lr"}],"next_cursor":null}