StackScholar

RAG & Agents

Reciprocal Rank Fusion (RRF)

Fusing ranked lists by summing 1/(k + rank) across systems, with k typically 60.

Why interviewers ask about it

Rank-based, so it needs no score normalisation - robust when BM25 scores are unbounded and cosine is in [−1, 1]. The safer default over weighted score fusion.

Related terms

Hybrid Search

Combining dense vector retrieval with sparse lexical retrieval (BM25), usually fused by reciprocal rank fusion.

Cross-Encoder Reranking

Scoring (query, document) pairs jointly with full attention between them, applied to the top 20–100 candidates.

This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.