Verified90% confidenceFactTime unknown
The in-context learning capability of Few-Shot prompting was first systematically described in the GPT-3 paper.
11
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGPT-3之后研究者发现通过精心设计的提示，单一大模型即可零样本或少样本完成多类任务，这一范式被称为In-Context Learning84% similarUnverifiedPrompt engineering originated from the in-context learning phenomenon discovered by researchers after the release of GPT-3 in 2020.75% similarUnverifiedSelf-supervised learning is the training foundation of the GPT series of models, which learn by predicting the next masked word in text.75% similarUnverified2020年后，以GPT-3为代表的纯解码器自回归模型凭借涌现能力和少样本学习特性确立了主流地位72% similarUnverifiedPrompt engineering emerged in the GPT-3 era and has evolved through paradigms such as Chain-of-Thought, Few-shot Learning, and ReAct.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16096API
curl https://kongchang.com/api/v1/knowledge/claims/16096MCP
get_claim(id=16096)