How does Reciprocal Rank Fusion (RRF) work?
mediumAnswer
- For each doc d, compute RRF score = sum over retrievers r of , with k=60 typically.
- Rank-based (doesn't need score calibration between retrievers of different scales — critical since BM25 scores and cosine similarities are on different scales).
- Robust, simple, no learned parameters.
- Standard fusion for hybrid dense + BM25 search.
- Alternative: learned fusion via a small cross-encoder on top-N candidates.
Check yourself — multiple choice
- Sum raw scores
- Rank-based fusion: score = Σ — no score calibration needed, simple, robust standard for hybrid
- Only max score
- Random pick
RRF: rank-based fusion (Σ 1/(k+rank)); avoids score-scale calibration issues.
#retrieval#hybrid-search
Practise LLMs & GenAI
214 interview questions in this topic.
Related questions
- Why combine dense (vector) and sparse (BM25) retrieval?
- Why does hybrid search usually beat pure vector search?
- How does Retrieval-Augmented Generation (RAG) work?
- What are text embeddings and how are they used?
- How should you chunk documents for RAG?
- Walk through the components of a production RAG pipeline.