Unverified50% confidenceFactExact time
Reciprocal rank fusion (RRF) takes 1/(k + rank) for each document in each result list (k is usually 60), sums them, and reranks by total score; it relies only on ranks and requires no normalization.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRRF is a tuning-free rank fusion algorithm that uses only rank positions, accumulating scores as 1/(k+rank), with the constant k typically set to 60.78% similarVerifiedHybrid retrieval typically merges results from two retrieval pipelines using a weighted combination via the RRF (Reciprocal Rank Fusion) algorithm.73% similarVerifiedRRF (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.69% similarUnverifiedNDCG@K takes into account both relevance strength and ranking position, assigning a relevance score to the document at each position and applying logarithmic discounting by ranking position, and finally dividing by the ideal ranking score for normalization so that the result falls between 0 and 1.69% similarVerifiedReranking is typically implemented using cross-encoders, which concatenate the query and candidate documents before feeding them in together; it usually reranks only the Top-50 to Top-100 candidates and finally selects Top-3 to Top-5 to pass to the generative model.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057834API
curl https://kongchang.com/api/v1/knowledge/claims/1057834MCP
get_claim(id=1057834)