Unverified50% confidenceFactExact time
In ChatGPT's training, the pre-training phase uses unsupervised learning for next-token prediction, the instruction fine-tuning phase introduces supervised learning, and finally RLHF is used to align the model's outputs.
1
Sources
50%
Confidence
Long-term
Relevance
9/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedRLHF（基于人类反馈的强化学习）是ChatGPT等对话模型背后的关键训练技术77% similarVerifiedModern large language models typically go through three training stages: pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF).77% similarUnverifiedThe core working principle of large language models such as ChatGPT and Claude is next-token prediction based on massive training data.77% similarVerified大语言模型的预训练阶段本质上属于自监督学习，是一种特殊的非监督学习，模型通过预测下一个词来从海量文本中自动学习语言规律75% similarUnverifiedBERT uses Masked Language Modeling as its pre-training task, while GPT uses Causal Language Modeling (predicting the next word) as its pre-training task.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/936597API
curl https://kongchang.com/api/v1/knowledge/claims/936597MCP
get_claim(id=936597)