[KongchangAI]
Conceptsingle completion training

Single-Completion Training

An optimization approach that trains using only single-completion samples, which can reduce the computational overhead associated with multi-sample generation.

Timeline (last 90 days)

Nov 3

@k pressure can be fully realized through single-completion training, matching the performance of multi-completion @k optimizers at only a fraction of their cost.

Unverified50%
Nov 3

Single-completion training means that at each policy update, only one completion is sampled per prompt, yet the learning pressure of the @k objective is simulated through reward transformation or regularization design.

Unverified50%

All Facts (2)

Source Articles