Post-training (RLHF, RLVR and after)
Where a raw predictor becomes an assistant — and, lately, a reasoner.
Stai visualizzando una scheda concettuale: cosa significa questo termine in linguaggio chiaro, e i record che mette in relazione.
After pre-training, models are shaped: supervised fine-tuning on demonstrations, RLHF against human preferences, and now reinforcement learning on verifiable rewards (math checkers, passing tests) that produced the reasoning models. Post-training's share of total compute is rising sharply — labs describe it as the new frontier of differentiation, which is why data-labeling firms and RL environments became strategic assets.
Come si collega al resto dello stack
I collegamenti di questa scheda a colpo d'occhio — clicca un gruppo per raggiungerlo.
Correlati
Fonti
DeepSeek-R1 (RL for reasoning) ↗
Record revisionato al 2026-01-15 — vedi Metodologia.