Uncertainty in the Verbalizable Workspace

Epistemic status: We found useful uncertainty signal in three reasoning models. All experiments were run on three seeds and are fully reproducible. Whether the same approach can become a broader tool for monitoring models is still an open question. Lingo might include “intend” or “conscious” and has to be taken with a grain of salt.TL;DR: We provide an uncertainty estimation method for reasoning models. Building on the J-lens, we construct four orthogonal directions in a model’s hidden-state spa...