# RAG fusion

**Source:** https://promtable.com/glossary/rag-fusion

> RAG fusion runs multiple query rewrites in parallel against the retrieval index and fuses the ranked results — improving recall on ambiguous or multi-aspect queries.

---
RAG fusion runs multiple query rewrites in parallel against the retrieval index and fuses the ranked results — improving recall on ambiguous or multi-aspect queries.

Standard RAG retrieves on the user's original query. RAG fusion generates 3-5 query variants (semantic rewrites, more specific reformulations, synonym expansions), runs retrieval on each, and combines the ranked lists with reciprocal rank fusion. Empirically improves recall on ambiguous queries where the original wording misses relevant documents. Adds latency + LLM cost for the rewrite step but is cheap relative to a wrong answer. Pairs naturally with re-ranking the fused candidate set.

## When to use

- Ambiguous user queries ("how do I X" with multiple plausible meanings).
- Multi-aspect queries that need different docs for different parts.

## Common mistakes

- Generating too many variants — diminishing returns past ~5 and cost climbs linearly.
- Skipping the re-rank step — fusion fuses noise without filtering.

## Related terms

- [rag](https://promtable.com/glossary/rag)
- [hybrid-search](https://promtable.com/glossary/hybrid-search)
- [semantic-search](https://promtable.com/glossary/semantic-search)
- [self-consistency](https://promtable.com/glossary/self-consistency)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/rag-fusion
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/rag-fusion".
Contact: info@vibecodingturkey.com.