Verified65% confidenceFactExact time
In-Context Learning (ICL) refers to the ability of large language models to perform new tasks without updating weights, solely by providing examples or instructions in the input prompt; this ability was first systematically described in the GPT-3 paper.
3
Sources
65%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Claude Code高阶实战：打造顶级AI开发流
Related Claims
VerifiedThe effectiveness of prompt engineering is rooted in the large language model's In-Context Learning capability, which enables task switching without modifying model weights.82% similarUnverifiedIn-context learning (ICL) refers to the ability of large language models to perform new tasks without updating weights, simply by providing examples or instructions in the input prompt, a capability first systematically described in the GPT-3 paper76% similarUnverifiedWhen there are excellent writing examples in the context history, the model tends to follow the superior paradigm, which is related to the in-context learning capability of large language models.70% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/587664API
curl https://kongchang.com/api/v1/knowledge/claims/587664MCP
get_claim(id=587664)