Unverified50% confidenceFactExact time
Traditional 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.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在RAG系统中检索结果按相关性分数排序拼接，最相关chunk不一定排在最显眼位置，可能因位置不当被模型忽视74% similarUnverifiedOff-the-shelf systems encapsulate RAG details as a black box with no user intervention possible, making it difficult to investigate the cause when the agent gives a wrong answer—this is the most notable limitation compared to a self-built RAG workflow.74% 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73% similarUnverifiedPure vector RAG is prone to a dilemma in scenarios requiring multi-hop reasoning or precise attribution, where relevant content is retrieved but cannot be explained.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963395API
curl https://kongchang.com/api/v1/knowledge/claims/963395MCP
get_claim(id=963395)