single mention · post-training
p-norm aggregation of format signals
P-norm aggregation of format signals combines multiple format-quality signals into a single multiplier on the environment reward.1 Each signal is rescaled to a configurable strength, and the norm p controls how quickly simultaneous format defects compound in reducing the reward.2
Trade-off It lets a single format defect significantly lower the reward while guaranteeing the environment reward remains the primary training signal.3
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
The final reward Ri of environment i is computed by scaling the environment reward Renv i > 0 with a p-norm aggregation of format signals
— tech reportthe aggregation norm p controls how quickly simultaneous defects compound
— tech reportallows a single format signal to have a significant impact on the final reward, while ensuring that environment reward remains the primary training signal
— tech report
Filed under post-training › reward modelling