Post-training (RLHF, RLVR and after)
Where a raw predictor becomes an assistant — and, lately, a reasoner.
현재 보고 계신 것은 개념 설명 레코드입니다: 이 용어의 의미를 쉬운 말로 풀어쓰고, 연관된 레코드들을 연결합니다.
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.
전체 스택에서의 연결 구조
이 레코드의 링크를 한눈에 확인하세요 — 그룹을 클릭하면 해당 위치로 이동합니다.
출처
DeepSeek-R1 (RL for reasoning) ↗
검토 기준일 2026-01-15 — 보기 방법론.