What is Dense Retrieval?

Why does Dense Retrieval matter?

It can retrieve paraphrases and semantic matches that share few exact words, complementing lexical methods such as BM25.

Dense Retrieval in practice

Train or select an embedding model for the domain, index candidate vectors, and evaluate retrieval recall before connecting the results to generation.

What is the common confusion about Dense Retrieval?

Dense retrieval is not a reranker. It searches the collection, while a reranker rescores a smaller candidate set.

Learn Dense Retrieval in the course

Lessons that name Dense Retrieval in a title or section

• Information Retrieval and Search

  BM25 is precise but brittle. Dense casts a wide net but misses keywords. Hybrid is the 2026 default. Everything else is tuning.

  Phase 05: NLP: Foundations to Advanced

• Hybrid Retrieval with BM25 and Dense Embeddings

  Lexical and semantic retrieval fail on opposite query distributions. Hybrid retrieval with reciprocal rank fusion does not interpolate, it votes - and the vote wins on every query class.

  Phase 19: Capstone Projects

Covered in Phase 05: NLP: Foundations to Advanced and Phase 19: Capstone Projects.

Related terms

• EmbeddingA learned mapping from discrete items (words, images, users) to dense vectors in continuous space, where similar items end up close together
• Semantic SearchRetrieval that represents a query and candidates in an embedding space and ranks candidates using a vector-similarity function.
• BM25A lexical ranking function that scores a document from query-term matches while accounting for term rarity, repeated occurrences, and…
• Hybrid RetrievalRetrieval that combines signals from different methods, commonly lexical matching and dense-vector similarity, before merging or reranking…
• Reciprocal Rank Fusion (RRF)A rank-fusion method that combines several result lists by summing contributions that decrease with each item's rank in each list.

Sources

• Dense Passage Retrieval

More terms in Retrieval & generation

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

Open the Retrieval & generation list in the glossary