RAG & RetrievalTechnical Definition

Cross-Encoder Reranking

Reranking is a two-stage retrieval process that scores an initial batch of retrieved documents using a cross-encoder model to surface the most relevant passage to the top.

Core Technical Definition

Cross-encoder reranking is a secondary relevance scoring pass that jointly evaluates the query and retrieved candidate chunks to reorder them with high semantic precision before LLM synthesis.

How Reranking works in practice

Initial vector retrieval is fast (bi-encoder), computing similarities independently. However, bi-encoders can miss subtle semantic relationships.

A reranker takes the top-20 retrieved candidates and scores each candidate against the query simultaneously, pushing the true answer to position #1.

How SiteMind implements Reranking

SiteMind applies Reciprocal Rank Fusion (RRF) and relevance scoring across dense vector, full-text tsvector, and trigram candidates to ensure optimal chunk ranking before generation.

Test our AI tools in your browser (100% Free)

Estimate support savings, token counts, or test prompt injection security guardrails with our zero-cost sandboxes.

Explore Free Tools →