Unverified50% confidenceFactExact time
Retrieval-Augmented Generation (RAG) supplements a model's static knowledge through an external knowledge base, but does not alter the weights themselves
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
Unverified传统大模型依赖参数化知识（将文本编码进模型权重参数），而RAG引入非参数化知识（将外部文档库作为可实时检索的动态知识源）80% similarUnverified微调通过在私有数据上继续训练来更新模型权重，RAG则在不修改模型的前提下通过检索外挂知识库增强回答79% similarVerifiedRetrieval-Augmented Generation (RAG) architecture retrieves relevant structured data from an external knowledge base before the model generates a response, injecting it as context to produce more accurate answers.75% similarUnverified检索增强生成（RAG）范式由Lewis等人于2020年在Meta AI提出，核心思想是将参数化知识与非参数化知识相结合74% similarUnverifiedWhen needed, persistent knowledge is recalled by semantic relevance through RAG (Retrieval-Augmented Generation) technology and then injected into the Prompt.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930000API
curl https://kongchang.com/api/v1/knowledge/claims/930000MCP
get_claim(id=930000)