Unverified50% confidenceFactExact time
BM25 is a sparse retrieval algorithm that scores based on term frequency (TF) and inverse document frequency (IDF), introduces document length normalization and tunable parameters k1 and b, and does not rely on vector embeddings.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedBM25 is a bag-of-words model that focuses only on term frequency without understanding word order or semantics, but is more reliable for exact term matching and does not suffer from the semantic drift problem of vector retrieval.79% similarVerifiedBM25 and TF-IDF are classic representatives of lexical retrieval, based on literal keyword matching and term frequency statistics.78% similarUnverifiedThe core mechanism of BM25 is based on three factors—term frequency (TF), inverse document frequency (IDF), and document length normalization—making it sensitive to exact term matching but completely lacking in semantic understanding77% similarUnverifiedBM25是信息检索领域经典的基于词频的稀疏检索算法，由Robertson等人于1994年提出72% similarUnverifiedBM25引入词频饱和和文档长度归一化两个关键饱和函数72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069466API
curl https://kongchang.com/api/v1/knowledge/claims/1069466MCP
get_claim(id=1069466)