Reference Calibration
A one-time preprocessing step in the KAPPO pipeline that uses a reference model to estimate the baseline difficulty or baseline reward level of each prompt over the task distribution.
Timeline (last 90 days)
The researchers propose @k Adaptive Pressure for Policy Optimization (KAPPO), whose workflow includes a one-time reference calibration, after which existing @1 methods are adapted to @k through prompt-adaptive regularization or reward transformation.
Reference calibration is a one-time preprocessing step in the KAPPO workflow: before formal training, the reference model is used to estimate each prompt's baseline difficulty or baseline reward level over the task distribution, providing a normalized baseline for subsequent prompt-adaptive regularization.
All Facts (2)
Reference calibration is a one-time preprocessing step in the KAPPO workflow: before formal training, the reference model is used to estimate each prompt's baseline difficulty or baseline reward level over the task distribution, providing a normalized baseline for subsequent prompt-adaptive regularization.
50%UnverifiedThe researchers propose @k Adaptive Pressure for Policy Optimization (KAPPO), whose workflow includes a one-time reference calibration, after which existing @1 methods are adapted to @k through prompt-adaptive regularization or reward transformation.
50%