Unverified50% confidenceFactExact time
Traditional retrieval-augmented generation (RAG) approaches are passive, only retrieving relevant content when a query is received, triggered externally, with the model itself not deciding what or when to retrieve.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大多数RAG（检索增强生成）实现只解决了'检索到什么'的问题，却忽视了检索到的内容是否可信、是否互相矛盾的更深层问题79% similarPartially Verified传统RAG采用固定的单向流程（一次检索、一次生成），无法自动重试或换一种方式检索77% similarVerified检索增强生成（RAG）是主流幻觉抑制技术，在模型生成回答前从外部知识库检索相关文档片段作为上下文注入提示词76% similarUnverifiedTraditional RAG typically treats retrieval as a black-box step: a single vector query fetches Top-K results and places them directly into the context for the large model, and when retrieval quality is poor, the model generates content on weak or incorrect context, producing hallucinations without warning.73% similarVerifiedRetrieval-Augmented Generation (RAG) cannot completely eliminate hallucinations, as the model may still misinterpret retrieved documents or fill in gaps on its own when retrieval results are insufficient.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972402API
curl https://kongchang.com/api/v1/knowledge/claims/972402MCP
get_claim(id=972402)