Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- OpenAI o1 System Card
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey on Large Language Models for Code Generation
- Safety in Large Reasoning Models: A Survey
- D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
- Mitigating Deceptive Alignment via Self-Monitoring
- DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
- Scheming AIs: Will AIs fake alignment during training in order to get power?
- Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
- Solving math word problems with process- and outcome-based feedback
- Alignment faking in large language models
- SafeRBench: Dissecting the Reasoning Safety of Large Language Models
- SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Large Reasoning Models Learn Better Alignment from Flawed Thinking
- gpt-oss-120b & gpt-oss-20b Model Card
- Qwen3Guard Technical Report
- 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
- Chain-of-Thought Hijacking
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems