Why does hybrid search usually beat pure vector search?
mediumAnswer
- Because the two methods fail on different queries.
- Dense embeddings capture meaning and handle paraphrase well, but they blur exact tokens, so product codes, error numbers, rare names and version strings get lost.
- Lexical scoring, such as BM25, nails those exact matches but misses synonyms entirely.
- Combining them, usually with reciprocal rank fusion, recovers both regimes and the failures rarely overlap.
- This matters most in technical corpora, where the important query terms are precisely the identifiers embeddings handle worst.
- Add a cross-encoder reranker over the fused candidates for the largest additional gain.
Check yourself — multiple choice
- It is just faster
- Dense search handles paraphrase but blurs exact identifiers, lexical search does the opposite — fusing them covers both, and a reranker adds more
- BM25 is always better
- Hybrid search is obsolete
Dense and lexical retrieval fail on complementary queries, so fusion raises recall.
#hybrid-search#reranking#retrieval
Practise LLMs & GenAI
214 interview questions in this topic.