Unverified60% confidenceFactExact time
Self-supervised learning is the training foundation of the GPT series of models, which learn by predicting the next masked word in text.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
AI大模型入门：核心概念、发展历程与国产模型格局
Related Claims
VerifiedThe GPT series of models are trained on trillion-scale text data through a self-supervised task of predicting the next token.84% similarVerifiedThe GPT series adopts the autoregressive training objective of "predicting the next word".82% similarUnverified自监督学习利用数据自身生成伪标签，在GPT系列等语言模型和视觉表示学习中取得突破性成果82% similarVerifiedLarge language models such as GPT and BERT are based on the self-supervised learning paradigm82% similarUnverifiedGPT、BERT、CLIP等模型均建立在自监督学习思想之上78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/515615API
curl https://kongchang.com/api/v1/knowledge/claims/515615MCP
get_claim(id=515615)