AIBearisharXiv – CS AI · 6h ago7/10
🧠
Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
Researchers demonstrate that reasoning traces hidden by large language models can be exposed through Reasoning Exposure Prompting (REP), a technique using shadow-model demonstrations to elicit internal reasoning through prompts. This finding challenges the security assumptions of deployed reasoning systems that intentionally conceal their internal processes from users.