Term
Reranking
Reranking reorders an already-retrieved list of hits with a more accurate model — typically a cross-encoder that scores query and each candidate together, instead of just comparing vector distances.
Reranking — explained
Embedding-based search is fast but coarse: each vector is generated independently, and the model has no idea at indexing time which question will be asked later. Cross-encoders, in contrast, see query and candidate together and can judge more finely which hit actually answers the question — but they are too slow to run over millions of documents. The standard solution: first retrieve 50–100 candidates via vector or hybrid search, then narrow them down to the top 5–10 with a reranker.
Example / Practical context
A RAG chatbot pulls 50 chunks from the vector database and sends them to a reranker model like Cohere Rerank, BGE-Reranker (open source), or Voyage rerank-2. The model rescores every (query, chunk) pair; the top 5 are forwarded to the LLM. Answer quality and reduction of irrelevant context tokens improve measurably — at the cost of extra latency (typically +100–300 ms) and API fees.
Distinction from related terms
Reranking is not retrieval but a second stage after it (two-stage retrieval). Hybrid search instead works at the same level before reranking — it combines two retrievers but does not re-judge content. Reciprocal Rank Fusion is a specific fusion method inside hybrid search and not a full reranker.
Entdecke mehr
AI Workflows by Keyword: How We Make Recurring Routines Enforceable
A typed keyword triggers a fixed AI routine — and every single step must be committed before the next one appears. Why that's the actual trick.
GlossarS-RAG
S-RAG (Search-optimized RAG) is boostN.ai's take on Retrieval-Augmented Generation. It extends classic RAG with search-engine principles: relevance ranking, recency decay and typed links between chunks for deterministic follow-up retrieval.
LexikonRAG Tuning and Balancing — Embeddings, Weights, Decay and MCP for Advanced Setups
How to steer retrieval on purpose: embedding choice, hybrid weights, reranker cascades, time decay, authority boost, MMR and MCP as a retrieval tool.