ModelRefs / Reciprocal Rank Fusion (RRF) — AI Glossary

Reciprocal Rank Fusion (RRF) — AI Glossary

A rank fusion algorithm that merges multiple ranked retrieval lists by summing reciprocal rank scores. Simple, robust, and empirically strong. Also called RRF.

Overview

RRF (Cormack et al., 2009) combines BM25 and vector retrieval rankings without requiring score normalization. Simple, robust, and empirically strong. The standard fusion method in hybrid search pipelines.

Reference details

Topicrag
Also known asRRF
Last reviewed2026-06-24

Commonly confused with

The usual way hybrid search combines its two result lists, and its defining property is that it uses only rank position, never the underlying scores. That is deliberate: BM25 scores and cosine similarities are on incomparable scales, so any attempt to combine them numerically requires a normalisation that has to be tuned and re-tuned. Ranks need no such calibration, which is why this is the default.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Reciprocal Rank Fusion (RRF) — AI Glossary.

Frequently asked questions

What is Reciprocal Rank Fusion (RRF)?

A rank fusion algorithm that merges multiple ranked retrieval lists by summing reciprocal rank scores.

Is Reciprocal Rank Fusion (RRF) the same as RRF?

Yes — RRF are common aliases for Reciprocal Rank Fusion (RRF).

What concepts are related to Reciprocal Rank Fusion (RRF)?

Closely related concepts include hybrid search, bm25, semantic search.