Verified65% confidenceFactExact time
BM25 is more stable and reliable than vector retrieval in exact lexical matching scenarios (such as product model numbers, proper nouns, and contract clause numbers)
3
Sources
65%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
企业级RAG知识库落地的5大工程硬伤：从Demo到生产的真实门槛
bilibili赋范课堂7/4/2026
Related Claims
UnverifiedPure vector semantic retrieval may overlook the need for exact keyword matching, which is why the industry has shifted toward hybrid retrieval (combining BM25 with vector semantic retrieval) to improve recall and precision.73% similarUnverifiedHybrid retrieval combining vector similarity and keyword-based BM25 can significantly improve recall accuracy.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/180995API
curl https://kongchang.com/api/v1/knowledge/claims/180995MCP
get_claim(id=180995)