Home · Glossary · Re-ranking
Enterprise AI glossary · RAG & Retrieval

Re-ranking

A second-stage retrieval step where a more expensive model rescores the top-N initial results to surface the truly most relevant ones to the top.

Definition

What Re-ranking means in practice

Re-ranking is a second-stage retrieval pass. The initial dense+sparse retrieval pulls the top 30–100 candidate chunks, then a cross-encoder model rescores each candidate against the query and the top 3–8 are passed to the LLM. The cross-encoder is more expensive per pair than the bi-encoder used for initial retrieval (it attends to query and candidate together), but it only sees a small candidate set, so latency cost is bounded. Re-ranking typically lifts answer accuracy 8–15 points on long-document corpora. The default open-weights re-ranker for sovereign deployments is bge-reranker-v2-m3 — runs acceptably on CPU for low-traffic deployments, on a small GPU for production.

Go deeper
Enterprise RAG architecture →

All 62 terms, in plain language

Sovereign AI, RAG, agentic AI, IDP, MLOps and the regulations that shape enterprise AI.

Browse the glossary →Talk to an engineer →