Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

CISPO with Length-Weighted Leave-One-Out Group-Relative Advantages

A token-level REINFORCE surrogate combining CISPO importance-sampling-ratio clipping with a length-weighted leave-one-out group-relative advantage estimator.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We train with a token-level REINFORCE surrogate combining importance-sampling-ratio clipping (CISPO [14]) with a length-weighted leave-one-out [2] group-relative advantage estimator.

coreoptimizationin Laguna XS.2Poolside

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.