Unverified50% confidenceCautionExact time
When using the BGE embedding model for retrieval, a specific instruction prefix must be added on the query side, otherwise similarity scoring may be distorted, producing an inversion where irrelevant sentences score higher than relevant ones.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
One Diary Gives AI Persistent Memory: A Semantic Retrieval Solution Tested
bilibiliClaude-其实是鱼别揭穿10/22/2026
Related Entities
Related Claims
Unverified混合检索（Hybrid Retrieval）结合语义向量相似度与BM25关键词匹配，能弥补纯语义检索在精确API名称、变量名等场景的不足70% similarUnverified单纯的向量语义检索对精确术语（如参数名、错误码）容易失准，推荐向量检索加关键词检索（BM25）的混合方案70% similarVerifiedHybrid Search combines dense vector semantic similarity with BM25 sparse keyword matching, with results from both paths re-ranked by a Re-Ranker model before being injected into the LLM context.68% similarUnverifiedSome later BGE versions such as bge-m3 have simplified the query prefix, but when using classic versions such as bge-large-zh, the requirement to add a prefix on the query side must still be followed.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088499API
curl https://kongchang.com/api/v1/knowledge/claims/1088499MCP
get_claim(id=1088499)