Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / reranker

Reranker

A cross-encoder model that re-scores a candidate set of documents — typically the top-k from an initial vector or hybrid retrieval — to improve ordering by the actual query-document semantic match.

What this means in practice

Trades additional latency for significant precision gains on the top few results; required for production RAG at retrieval-heavy use cases.

Synonyms

cross-encoder reranker , reranking model

Related Terms Network

This diagram shows how Reranker connects to other concepts in the COMPEL body of knowledge. Each linked node is a term you can explore in turn.

Related terms for Reranker Network graph showing 2 related glossary terms connected to Reranker. Reranker Hybrid ret… Embedding …
2 related concepts connected to Reranker.

The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.

Accessible list of related terms
  • Hybrid retrieval — A retrieval pattern combining dense (vector-based, e.g., dense passage retrieval) and sparse (term-based, e.g., BM25) retrieval methods, whose candidate sets are fused — typically via reciprocal rank fusion — before reranking.
  • Embedding model — A model that maps text, images, or multimodal content to dense vector representations used for retrieval, clustering, and similarity search.

See also

  • Hybrid retrieval — A retrieval pattern combining dense (vector-based, e.g., dense passage retrieval) and sparse (term-based, e.g., BM25) retrieval methods, whose candidate sets are fused — typically via reciprocal rank fusion — before reranking.
  • Embedding model — A model that maps text, images, or multimodal content to dense vector representations used for retrieval, clustering, and similarity search.