ModelRefs / Maximal Marginal Relevance (MMR) — AI Glossary
Maximal Marginal Relevance (MMR) — AI Glossary
A retrieval re-ranking algorithm balancing relevance to the query with diversity among selected documents.
Overview
MMR (Carbonell & Goldstein 1998) selects documents iteratively: pick the next document that maximizes relevance to the query minus similarity to already-selected documents. Prevents redundant, near-duplicate passages from filling the context window. Supported by LangChain retrievers and Pinecone, Weaviate, and Qdrant vector databases.
Reference details
| Topic | rag |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
A re-ranking step, but not a relevance reranker — a cross-encoder reranker asks which results are most relevant, while this asks which set is least redundant. Both reorder the candidates and they optimise for different things, so they compose: rerank for relevance, then apply this to stop the top-k being five near-identical chunks that crowd out the one covering the rest of the answer.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Maximal Marginal Relevance (MMR) — AI Glossary.
Frequently asked questions
What is Maximal Marginal Relevance (MMR)?
A retrieval re-ranking algorithm balancing relevance to the query with diversity among selected documents.
What concepts are related to Maximal Marginal Relevance (MMR)?
Closely related concepts include fusion retrieval, dense retrieval, context management.