On the Rejection Criterion for Proxy-based Test-time Alignment

ArXi:2604.16146v1 Announce Type: new Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large model distribution, whereas the nudging approach defers the generation of the next token to the small aligned model when the large base one is unconfident about its outcome.