← All parts of this equation

Equation 14 · Part 4 · Naive, Graph, and Agentic: A Systems Comparison of RAG Architectures

Symbol k

RRF(d)=∑r∈R1k+r(d),\mathrm{RRF}(d) = \sum_{r \in R} \frac{1}{k + r(d)},
kk

What this part means

the smoothing constant.

Its job in the formula

k occurs below the fraction bar. The quantity above the bar is divided by this expression; zero is excluded as a denominator.

Where the article explains it

Reciprocal rank fusion, which Cormack and colleagues introduced and showed outperforming both individual rankers and a Condorcet-style combination, ignores raw scores entirely and combines rank positions across retrievers R with a smoothing constant k , RRF(d)=∑r∈R1k+r(d)\mathrm{RRF}(d) = \sum_{r \in R} \frac{1}{k + r(d)}.

The passage around this formula

…Cormack and colleagues introduced and showed outperforming both individual rankers and a Condorcet-style combination, ignores raw scores entirely and combines rank positions across retrievers R with a smoothing constant k , RRF(d)=∑r∈R1k+r(d)\mathrm{RRF}(d) = \sum_{r \in R} \frac{1}{k + r(d)}. sidestepping the problem that a BM25 score and a cosine similarity are not directly comparable quantities [ 3 ] . A reranking stage — typically a cross-encoder scoring each retrieved candidate jointly with the query — can then sit downstream of the fused list and reorder it…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.