Sparse retrieval (BM25) vs dense retrieval (ANN) — when to hybrid?

Sparse retrieval (BM25) vs dense retrieval (ANN) — when to hybrid?medium

Type: conceptual
Topic: sparse-retrieval-bm25-vs-dense-retrieval-ann-when-to-hybri
Frequency: common
Tags: rag, sparse, retrieval, bm25, dense

Answer

BM25 is keyword-based — great for exact term matches and domain-specific jargon.

Explanation

BM25 is keyword-based — great for exact term matches and domain-specific jargon. Dense retrieval uses embedding similarity — better for semantic/paraphrase matches. Hybrid (RRF: Reciprocal Rank Fusion): run both, merge ranked lists. Use hybrid when queries mix exact terms and semantic meaning, or domain vocabulary is specialized (financial terms). Recommended for production RAG.

Follow-upWhen would you choose one approach over the other?