Unverified50% confidenceFactExact time
Post-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.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified后训练通常涵盖监督微调（SFT）、强化学习对齐（RLHF/RLAIF）以及领域适配微调，视觉推理模型还涉及视觉指令微调80% 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).79% 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79% similarVerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.77% similarUnverifiedA typical post-training pipeline is: pre-training → supervised fine-tuning (SFT) → preference optimization (RLHF / DPO / GRPO).76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995955API
curl https://kongchang.com/api/v1/knowledge/claims/995955MCP
get_claim(id=995955)