specific method · filed under post-training
Rejection sampling
A sampling method applied to reasoning traces; the evidence does not specify further details of the fine-tuning procedure.
Also called rejection sampling fine-tuning.
- sources
- 2
- models
- 2
- labs adopt it
- 2
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
rejection sampling fine-tuning and mask fine-tuning
usedpost trainingin GLM-5Z.ai
rejection sampling on those reasoning traces
useddata curationin Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under post-training :: supervised fine-tuning.
Supervised fine-tuningFine-tuningLight SFT on teacher-distribution dataLoRA fine-tuningSelf-correction cold startSFT bootstrapping with synthetic dataAdversarial fine-tuningAutoregressive fine-tuningCold-started SFT modelEvaluation-based early stoppingFine-tuning with demographically balanced datasetsFrozen-network warmup for new special tokensInstruction hierarchy trainingInstruction-following fine-tuningLightweight speaker fine-tuningPrompt-based cold start for tool useReasoning-data system promptSafety training to an internal specificationSFT checkpoint for RL researchSFT on MiMo-generated task dataSpecialist-model trainingSupervised fine-tuning at 256k sequence lengthToken-budget-based SFT data blending