Unverified50% confidenceFactExact time
RRF (Reciprocal Rank Fusion) weights and sums the results of two retrieval streams by the reciprocal of their ranks, requiring no score normalization, and is simple to implement with strong robustness.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedHybrid retrieval typically merges results from two retrieval pipelines using a weighted combination via the RRF (Reciprocal Rank Fusion) algorithm.79% similarUnverified混合检索通过RRF等算法融合向量嵌入与关键词检索两路结果，是当前工业界RAG系统的最佳实践69% similarUnverifiedHybrid retrieval, which fuses BM25 keyword scores with vector similarity scores through weighted combination (typically using the RRF reciprocal rank fusion algorithm), has become the mainstream paradigm for RAG systems.68% similarVerified混合检索（Hybrid Search）将向量检索与BM25关键词检索的结果通过RRF（倒数排名融合）等算法合并，兼顾语义理解与精确匹配67% similarVerifiedHybrid retrieval combines BM25 sparse retrieval with dense vector retrieval, merging ranking results via RRF or linear weighting.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916138API
curl https://kongchang.com/api/v1/knowledge/claims/916138MCP
get_claim(id=916138)