Unverified50% confidenceFactExact time
RAG检索增强生成由Lewis等人于2020年在Facebook AI Research提出，核心在于将参数化知识与非参数化知识解耦，使知识更新无需重新训练模型
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedRAG (Retrieval-Augmented Generation) was proposed by Lewis et al. in 2020, with the core idea of decoupling parametric knowledge from non-parametric knowledge and dynamically retrieving relevant documents to concatenate into the prompt at inference time.79% 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78% similarUnverifiedRAG论文的核心洞察是参数化知识（存储在模型权重中）与非参数化知识（存储在外部检索库中）可以有机结合69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/523893API
curl https://kongchang.com/api/v1/knowledge/claims/523893MCP
get_claim(id=523893)