What is Maximum Marginal Relevance (MMR)?

Why does Maximum Marginal Relevance (MMR) matter?

It can reduce redundant chunks so a limited context budget covers more distinct evidence.

Maximum Marginal Relevance (MMR) in practice

Retrieve a candidate pool, select the next item using a documented relevance-diversity weight, and evaluate both answer quality and source coverage.

What is the common confusion about Maximum Marginal Relevance (MMR)?

MMR diversifies an existing candidate set; it does not retrieve missing evidence or prove that selected passages are correct.

Learn Maximum Marginal Relevance (MMR) in the course

No lesson links to this term yet. Search the course catalog for it.

Related terms

• RerankerA second-stage model or scoring function that reorders a small candidate set using a richer comparison between the query and each candidate.
• ChunkingDividing source material into retrievable units before indexing. Chunk boundaries, overlap, metadata, and document structure determine…
• RAG (Retrieval-Augmented Generation)A system pattern that retrieves evidence relevant to a request and supplies selected content to a generative model before it answers or…
• GroundingConnecting a generated answer or action to evidence, state, or observations that the system can identify and check.

Sources

• The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries

More terms in Retrieval & generation

• Approximate Nearest Neighbor (ANN)
• BM25
• Chunking
• Dense Retrieval
• Grounding
• HNSW
• Hybrid Retrieval
• RAG (Retrieval-Augmented Generation)
• Recall@K
• Reciprocal Rank Fusion (RRF)
• Reranker
• Semantic Search
• Vector Database

Open the Retrieval & generation list in the glossary