Unverified50% confidenceFactExact time
SFT（监督微调）是ChatGPT等对话模型训练流程的第一阶段
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedSFT（监督微调）用人工标注的提示-回答对直接优化模型输出分布，InstructGPT、Alpaca等早期指令微调工作均以SFT为核心70% similarUnverifiedAfter enabling the Agent feature, ChatGPT's overall capability is in the first tier.69% similarUnverifiedMainstream LLM products such as ChatGPT, DeepSeek, Kimi, and Qwen have all gone through three core stages: pre-training, SFT, and preference alignment.68% similarUnverifiedSFT源自InstructGPT论文中提出的RLHF流程的第一阶段68% similarUnverifiedInstructGPT、ChatGPT及Claude等主流对话模型均以RLHF为核心对齐技术66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/527824API
curl https://kongchang.com/api/v1/knowledge/claims/527824MCP
get_claim(id=527824)