Unverified50% confidenceSolutionExact time
生产系统通常采用粗召回+精排的两阶段架构：Bi-Encoder召回Top20-50候选，Cross-Encoder重排后取Top3-5送入大模型
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
UnverifiedReranking uses a Cross-Encoder model to score candidate documents retrieved in the initial retrieval pairwise, then fine-ranks the Top-K to feed into the LLM.67% similarUnverifiedProduction-grade RAG systems commonly adopt a two-stage architecture of hybrid retrieval plus reranking, first using sparse retrieval (such as BM25) to recall candidate documents, then using a Cross-Encoder to rerank and select passages.67% similarUnverifiedReranking typically uses a CrossEncoder architecture that concatenates the query with candidate chunks for relevance scoring, and has become a standard coarse-ranking + fine-ranking two-stage architecture in industrial-grade RAG systems.65% similarVerified重排序（Re-ranking）机制在初步检索后引入交叉编码器（Cross-Encoder）对候选文档重新打分，提升输入大模型的上下文质量64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488691API
curl https://kongchang.com/api/v1/knowledge/claims/488691MCP
get_claim(id=488691)