Skip to content

Similar papers

What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation

On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since each update is conditioned on the reasoning prefix already generated by the student, the prefix also shapes how effectively teacher feedback is converted into learning. We fi...

Zi-Zhuo Lin, Quan-Ling Liu, Yi Yang et al. · 0 citations
Review Aug 2026

W HAT D OES AN E VALUATION L ICENSE ? A C OMMIT -B OUND C ENSUS OF C LAIM -R ELATIVE I NFERENCE IN I NSPECT E VALS

Evaluation artifacts specify a forward computation: a task, scorer, and reported metric. They do not necessarily license the claim attached to that metric because the historical evidence and alternative semantics needed to replay it may be unbound. We formalize this missing claim-replay layer through a frozen substrate...

Xi Qin · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.