Unverified50% confidenceTradeoffExact time
Global 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.
1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-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.77% 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.70% similarUnverifiedVector retrieval is inherently weak at multi-hop reasoning; when an answer requires synthesizing scattered information fragments from multiple documents, pure similarity ranking often fails to retrieve all necessary context.69% similarUnverifiedThe ranking factors of traditional search can be partially reverse-engineered and restored through statistical analysis, but the decision-making process of large language models with billions of parameters is nearly impossible to audit at the same level of granularity.68% similarUnverifiedThe challenge with score normalization is that when a knowledge base contains no truly relevant documents, the highest score after normalization may still be pushed up to the same level as relevant results from other bases, creating an illusion of high scores for irrelevant results.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/887386API
curl https://kongchang.com/api/v1/knowledge/claims/887386MCP
get_claim(id=887386)