What is Reranker?

A second-stage model or scoring function that reorders a small candidate set using a richer comparison between the query and each candidate.

Why does Reranker matter?

Fast first-stage retrieval maximizes candidate coverage, while reranking can improve which evidence reaches the limited context window.

Retrieve 50 candidates with hybrid search, score each query-document pair with a cross-encoder, and pass the top 5 supported chunks to generation.

A reranker does not search the entire corpus. It only reorders candidates that retrieval already found.

Lessons that name Reranker in a title or section

Cross-Encoder Reranker
A bi-encoder embeds query and document independently. A cross-encoder concatenates them and reads both at once. The cross-encoder is the smartest reader and the slowest.
Phase 19: Capstone Projects
Advanced RAG (Chunking, Reranking, Hybrid Search)
Basic RAG retrieves the top-k most similar chunks. That works for simple questions. It falls apart for multi-hop reasoning, ambiguous queries, and large corpora.
Phase 11: LLM Engineering

Hybrid RetrievalRetrieval that combines signals from different methods, commonly lexical matching and dense-vector similarity, before merging or reranking…
Semantic SearchRetrieval that represents a query and candidates in an embedding space and ranks candidates using a vector-similarity function.
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…
BM25A lexical ranking function that scores a document from query-term matches while accounting for term rarity, repeated occurrences, and…
ChunkingDividing source material into retrievable units before indexing. Chunk boundaries, overlap, metadata, and document structure determine…
Cosine SimilarityThe normalized dot product of two vectors. It compares their direction rather than their magnitude and ranges from -1 to 1 for real-valued…
GroundingConnecting a generated answer or action to evidence, state, or observations that the system can identify and check.
Maximum Marginal Relevance (MMR)A selection rule that balances relevance to the query with novelty relative to items already selected.
Recall@KFor one query, Recall@K is `|relevant items intersecting the top k| / |relevant items|`.
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.