Aller au contenu principal

Fuse Keyword And Vector Results

Explain how Reciprocal Rank Fusion combines keyword and vector result lists without comparing raw scores.

vector-search5 min read

The team needs to merge BM25 and vector results, but raw scores are not comparable across retrievers. Reciprocal Rank Fusion: combine ranked lists using rank positions, not raw score scales The common trap is averaging BM25 and vector scores without calibration. That makes the larger or more variable score dominate. List ranks BM25: A=1, B=2, C=3. Vector: B=1, C=2, A=3. Use each retriever's rank position; ignore raw score scale. Apply RRF With k=60, A gets 1/(60+1) + 1/(60+3). B gets 1/(60+2) + 1/(60+1). C gets 1/(60+3) + 1/(60+2). Higher ranks contribute slightly more, but agreement across lists matters. Sort fused…

Read the full lesson

Sign up free: one personalized lesson every day, matched to your role and goals.

← Back to library

Nous contacter