arXiv cs.CL
· Papers
Not All LLM Reasoning is Visible in the Chain-of-Thought
arXiv:2607.22925v1 Announce Type: new Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode where frontier models exhibit invisible reasoning by leveraging semantically irrelevant filler tokens to improve performanc