Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs

arXiv:2606.00642 · cs.AI, cs.CR · Submitted 2026-05-30 · Read on arXiv

cs.AI, cs.CR

Submitted: 2026-05-30

Updated: 2026-08-29

Terminology

• Trace — 190× in this paper · explained in 2 episodes
• Distillation — 40× in this paper · explained in 2 episodes
• Reasoning Traces — 22× in this paper · explained in 3 episodes
• Fidelity — 14× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Reasoning Exposure Prompting — 5× in this paper
• Scaffolding — 5× in this paper · explained in 3 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Cross-Model Transfer — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
• SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
• Reasoning Models Don't Always Say What They Think
• Training Verifiers to Solve Math Word Problems
• Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models
• Measuring Faithfulness in Chain-of-Thought Reasoning
• Orca: Progressive Learning from Complex Explanation Traces of GPT-4
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• How to Steal Reasoning Without Reasoning Traces

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection