Tom Goldstein

works on

kl regularization 1 language model reasoning 1 policy optimization 1 reinforcement learning 1 self-distillation 1 token-level mixing 1

From the 1 of 10 linked papers with an AI index.

collaborators

Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Not All LLM Reasoning is Visible in the Chain-of-Thought

Vatsal Baherwani, Tom Goldstein, Ashwinee Panda

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 i…