Open Models Almanac
Methodspost-trainingreward modelling

single mention · post-training

Multiplicative p-norm format reward

Uses a multiplicative p-norm variant to aggregate format signals rather than an additive combination.

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.

Also called multiplicative p-norm version.

Filed under post-training › reward modelling