Post-training (RLHF, RLVR and after)
概念
训练与推理
Where a raw predictor becomes an assistant — and, lately, a reasoner.
您正在查看一条概念解释记录：该术语的通俗含义，以及它所关联的各条目。
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.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
来源
DeepSeek-R1 (RL for reasoning) ↗
记录审阅截至 2026-01-15 — 查看 方法论.