Unverified60% confidenceFactExact time
A typical post-training pipeline is: pre-training → supervised fine-tuning (SFT) → preference optimization (RLHF / DPO / GRPO).
2
Sources
60%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLaMA-Factory integrates training algorithms such as incremental pre-training, instruction-supervised fine-tuning (SFT), reward model training (Reward Model), PPO, DPO, KTO, and ORPO.76% similarUnverifiedPost-training is a critical phase between the completion of large language model pretraining and actual usability, encompassing technical approaches such as supervised fine-tuning (SFT), instruction alignment, and RLHF/DPO.76% similarVerified"Post-training" is the alignment and capability enhancement phase following pre-training, and typically includes SFT, RLHF, and reinforcement learning based on process reward models (such as GRPO and DAPO).75% similarUnverifiedMinor version upgrades are carried out through post-training techniques such as supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), or direct preference optimization (DPO), at a lower cost than full pretraining.73% similarVerified从预训练检查点到可商用产品需经历监督式指令微调（SFT）和基于人类反馈的强化学习（RLHF）两个后训练阶段72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810413API
curl https://kongchang.com/api/v1/knowledge/claims/810413MCP
get_claim(id=810413)