Skip to content
BENIBIX Learn

Reciprocal Rank Fusion (RRF)

Also known as RRF, Rank Fusion

A way to join ranked lists. Each place earns points.

Think of it like

It is like two friends who rank the same films. A film near the top for both of them wins.

Example

In Lucy's shop search, one page is 2nd in the keyword list and 5th in the meaning list. It earns 1/62 plus 1/65, which beats a page that is 1st in only one list.

Why it matters

It is the usual way hybrid search joins its two lists. It needs no tuning, and the two scores never have to be on the same scale.

Definition

Reciprocal rank fusion, or RRF, is a way to merge two or more ranked lists into one. Each list gives a result 1 divided by 60 plus its place. So first place earns 1/61, and tenth place earns 1/70. The points from every list are added, and the top total comes first. It looks only at places, not scores, so lists with different kinds of score can be merged. It was published in 2009.
Fusion is the merge step on the right. It reads each result's place in both lists, not its score.

Common mistake

Adding the raw scores of the two searches instead. A keyword score and a cosine score are on different scales, so one list swamps the other.

Key takeaways

  1. 1
    Places, not scores. Only the rank in each list counts.
  2. 2
    One over 60 plus the rank. Points fall slowly down a list.
  3. 3
    Add across lists. Near the top of both wins.

Compare