Unverified50% confidenceFactExact time
Ranked retrieval typically relies on mechanisms such as BM25, bi-encoder models, or cross-encoders to place the most relevant documents at the top.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedProduction-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.74% similarUnverifiedReranking 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.72% similarUnverifiedReranking is typically implemented using cross-encoders, which concatenate the query and candidate documents before feeding them in together; it usually reranks only the Top-50 to Top-100 candidates and finally selects Top-3 to Top-5 to pass to the generative model.72% similarUnverifiedFTS5 默认使用 BM25 排序算法，综合考虑词频、逆文档频率和文档长度归一化71% similarUnverified大规模代码库的精准检索融合基于AST的结构化分析、向量嵌入技术和BM25等传统信息检索算法70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922249API
curl https://kongchang.com/api/v1/knowledge/claims/922249MCP
get_claim(id=922249)