Unverified50% confidenceSolutionExact time
Query rewriting in CRAG has the LLM decompose the original question into several more precise sub-queries, retrieve results separately, and then merge them, so as to reduce retrieval failures caused by the vocabulary gap.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn multi-turn conversations, elliptical queries with anaphora perform poorly when used directly for vector retrieval, so query rewriting using an LLM to rewrite them into self-contained queries is a common approach70% similarUnverified在RAG流程返回大量候选文档片段时，可先按相关性排序再截取前3-5项传入大模型以控制输入长度65% similarUnverified文本分块策略、检索召回数量（Top-K）、重排序模型（Reranker）是影响RAG系统最终效果的三个关键变量64% similarUnverifiedR²Adapter's rewriting function rewrites borderline queries to more clearly expose implicit multi-hop reasoning requirements, improving retrieval quality without the need for additional supervision signals.64% similarUnverifiedChunks that are too large dilute retrieval precision, while chunks that are too small result in incomplete semantics; the chunking strategy directly determines the retrieval quality of a RAG system.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955921API
curl https://kongchang.com/api/v1/knowledge/claims/955921MCP
get_claim(id=955921)