Promptwatch Logo

Reranking

Reranking is a second-stage retrieval step that reorders candidate documents by deeper relevance, improving the passages fed to an LLM in AI search and GEO.
Updated September 6, 2026
AI

Definition

Reranking is a second-stage retrieval process that takes an initial list of candidate documents—usually returned quickly by vector search or keyword search—and reorders them by relevance using a more accurate, computationally heavier model. The goal is to put the truly best passages at the top before they are passed to a language model, because most RAG systems only feed the top few results into the context window.

The typical pipeline has two stages. First, a fast retriever scans a large corpus and returns a broad candidate set (often dozens or hundreds of chunks) optimized for recall. Then a reranker—commonly a cross-encoder that jointly examines the query and each candidate—scores relevance with much higher precision and reorders the list. This two-stage design balances speed and accuracy: the retriever is cheap and broad, the reranker is expensive but precise and only runs on the shortlist.

Reranking matters because first-stage retrieval often surfaces topically related but not directly useful passages. A cross-encoder can capture nuance—negation, specificity, and intent—that embedding similarity misses, materially improving answer quality and reducing hallucinations. Hybrid systems frequently combine keyword search, vector search, and reranking together.

For GEO, reranking is part of how AI systems decide which sources to actually use. Content that directly and specifically answers a query—rather than loosely matching its keywords—is more likely to survive the rerank stage and be cited, reinforcing the value of answer-first, self-contained passages.

Examples of Reranking

  • A RAG pipeline retrieves 100 candidate chunks with vector search, then a cross-encoder reranker selects the 5 most relevant to send to the LLM, sharply improving answer accuracy.
  • A documentation search tool adds a reranking stage and finds that pages which precisely answer the query now outrank pages that merely mention the keywords.
  • An enterprise assistant combines keyword retrieval, embedding retrieval, and a reranker so both exact-match and semantically similar passages compete for the top slots.
  • A GEO team studies reranking by checking which of its passages survive to the top of retrieval for target queries, then rewriting weaker pages into direct, self-contained answers.

Terms related to Reranking

Vector Search

Vector search is a semantic search method that finds information by comparing embeddings—powering RAG, Perplexity, and AI search retrieval for GEO.

AI

Semantic Search

Semantic search is search technology that understands meaning, context, and intent behind queries using embeddings and NLP, not keyword matching alone.

SEO

Hybrid Search

Hybrid search combines keyword and vector retrieval so AI systems match exact terms and meaning—improving recall and citations in AI search.

AI

Embeddings

Embeddings are numerical vector representations of text or images that capture semantic meaning—core to vector search, RAG, and AI search retrieval.

AI

RAG (Retrieval-Augmented Generation)

RAG (retrieval-augmented generation) grounds LLM responses in real-time retrieved sources—core to AI search, Perplexity, and GEO citations.

AI

Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation (RAG) grounds LLM responses in real-time retrieved sources—core to AI search, Perplexity, and GEO citations.

AI

Passage Ranking

Passage ranking ranks individual passages within pages independently; most AI Overview citations come from URLs outside the top 20 results.

SEO

Retrieval Coverage

Retrieval coverage measures how much of your important content is accessible and likely to be retrieved by AI search and RAG systems.

Analytics

Context Engineering

Context engineering assembles the right information, tools, and memory into an LLM's context window so it produces accurate, grounded outputs for AI search.

AI

Frequently Asked Questions about Reranking

Learn about AI visibility monitoring and how Promptwatch helps your brand succeed in AI search.

Vector search is fast and optimized for recall, but it ranks by embedding similarity, which can surface topically related yet not directly useful passages. A reranker examines the query and each candidate together with higher precision, capturing nuance like specificity and negation that similarity scores miss.

Be the brand AI recommends

Monitor your brand's visibility across ChatGPT, Claude, Perplexity, and Gemini. Get actionable insights and create content that gets cited by AI search engines.

Promptwatch Dashboard