AI ART Discover · Learn · Create
AI Art > Glossary > Multi-Query Retrieval
Browse Full AI Glossary
M AI Glossary Term • Term 135 of 224
Plain English Definition

What does “Multi-Query Retrieval” mean?

Core Definition

A retrieval technique that rewrites the user query into several variants to improve recall.

Operational Mechanism

How Multi-Query Retrieval Works

Multi-Query Retrieval: User question feed into Model writes 3 rephrasings, each searched, which produces Union of results, duplicates removed.

Real-World Scenario

Practical Example

A user asks 'why is my app slow?'. The system also searches 'performance bottlenecks' and 'high latency causes', then merges the results so that relevant pages with different wording are found.

Core Significance

Why It Matters

People and documents use different words for the same idea. Multiple queries improve the chance of matching.

Expert Q&A

Common Questions About Multi-Query Retrieval

Q: Who generates the variants?

Typically a language model, prompted to rewrite the question in several ways.

Q: What is the downside?

More searches and more passages, which adds cost and can add noise.

Q: How is it different from hybrid search?

Multi-query varies the query wording; hybrid search varies the search method.