Unverified50% confidenceFactExact time
Vector retrieval can only answer what is similar to what, and cannot answer what is connected to what, why they are connected, or how they became connected.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGlobal queries can answer inductive questions requiring a macro perspective (such as the main themes across an entire document set), a scenario that pure vector retrieval is almost incapable of handling.67% similarUnverifiedRAG suffers from a scattered-answer problem because the current retrieval approach scores relevance between a query and individual chunks, making it difficult to guarantee that multiple complementary chunks are retrieved simultaneously.65% similarUnverifiedThe system prompt requires all responses to cite sources, and when retrieval results are irrelevant, it must respond with 'I don't know.'64% similarUnverifiedMulti-hop queries need to traverse multiple information nodes in a step-by-step manner, and vector retrieval is ill-suited for such scenarios due to its lack of a relational dimension.64% similarUnverified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62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/892613API
curl https://kongchang.com/api/v1/knowledge/claims/892613MCP
get_claim(id=892613)