Open Models Almanac
Methodspost-trainingreward modelling

single mention · post-training

Exploit-neutralization and regression-free patch reward

Rewards a patch only when it neutralizes an exploit while preserving existing test-suite passes.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reward modelling for the methods filed beside it.

Filed under post-training › reward modelling