Verified80% confidenceFactTime unknown
BM25（Best Matching 25）是由Stephen Robertson等人在1990年代提出的概率排序算法，基于词频、逆文档频率和文档长度归一化三个因素进行相关性打分
6
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Agentic RAG实战：原理剖析与LangChain代码实现指南
bilibiliAI大模型__
Related Entities
Related Claims
UnverifiedBM25核心机制基于词频（TF）、逆文档频率（IDF）和文档长度归一化三个因子，参数k1通常取1.2-2.0，b通常取0.7561% similarUnverifiedBM25 scores document relevance based on three factors: term frequency (TF), inverse document frequency (IDF), and document length normalization59% similarUnverified根据Artificial Analysis的独立评测，Glimmer 30B的智能指数得分为35分58% similarUnverified生产中典型做法是先用向量检索和BM25快速召回50-100个候选结果，再用reranker精排取top-k送入LLM57% similarUnverified混合精度训练中，FP16 每个参数占 2 字节显存，FP32 每个参数占 4 字节显存57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26802API
curl https://kongchang.com/api/v1/knowledge/claims/26802MCP
get_claim(id=26802)