What is Reciprocal Rank Fusion (RRF)?

Why does Reciprocal Rank Fusion (RRF) matter?

It can merge lexical, dense, or multi-query rankings without assuming their raw scores share the same scale.

Reciprocal Rank Fusion (RRF) in practice

Retrieve independent candidate lists, deduplicate by stable document identity, apply one versioned fusion constant, and evaluate against each individual retriever.

What is the common confusion about Reciprocal Rank Fusion (RRF)?

RRF combines ranks, not embeddings or relevance scores, and it cannot recover an item absent from every input list.

Learn Reciprocal Rank Fusion (RRF) in the course

Lessons that name Reciprocal Rank Fusion (RRF) in a title or section

• Information Retrieval and Search

  BM25 is precise but brittle. Dense casts a wide net but misses keywords. Hybrid is the 2026 default. Everything else is tuning.

  Phase 05: NLP: Foundations to Advanced

• Advanced RAG (Chunking, Reranking, Hybrid Search)

  Basic RAG retrieves the top-k most similar chunks. That works for simple questions. It falls apart for multi-hop reasoning, ambiguous queries, and large corpora.

  Phase 11: LLM Engineering

• Hybrid Retrieval with BM25 and Dense Embeddings

  Lexical and semantic retrieval fail on opposite query distributions. Hybrid retrieval with reciprocal rank fusion does not interpolate, it votes - and the vote wins on every query class.

  Phase 19: Capstone Projects

Covered in Phase 05: NLP: Foundations to Advanced, Phase 11: LLM Engineering and Phase 19: Capstone Projects.

Related terms

• Hybrid RetrievalRetrieval that combines signals from different methods, commonly lexical matching and dense-vector similarity, before merging or reranking…
• BM25A lexical ranking function that scores a document from query-term matches while accounting for term rarity, repeated occurrences, and…
• Dense RetrievalFirst-stage retrieval that embeds queries and candidates into vector representations and ranks candidates by a similarity function.
• RerankerA second-stage model or scoring function that reorders a small candidate set using a richer comparison between the query and each candidate.

Sources

• Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods

More terms in Retrieval & generation

• Approximate Nearest Neighbor (ANN)
• BM25
• Chunking
• Dense Retrieval
• Grounding
• HNSW
• Hybrid Retrieval
• Maximum Marginal Relevance (MMR)
• RAG (Retrieval-Augmented Generation)
• Recall@K
• Reranker
• Semantic Search
• Vector Database

Open the Retrieval & generation list in the glossary