# Reranking

> A second, slow look at the top hits. It puts them in a better order.

**Field:** Artificial Intelligence  
**Category:** Retrieval & Search  
**Also known as:** Re-ranking, Reranker, Cross-Encoder Reranking

## Think of it like

Think of it like a coach who picks 50 kids fast. Then the coach watches each one to choose the best 5.

## Definition

Reranking is a second pass that puts search results in a better order. A fast search first pulls, say, the top 50 candidates. Then a reranker model reads the question together with each candidate and gives it a new score. That is slower per text but much more accurate, so it is only run on the short list. The best few after reranking are the ones passed on to the user or the model.

## Example

Jack's search pulls 50 help articles in 20 milliseconds. A reranker reads each with the question and moves the one true answer from 14th place to 1st.

## Why it matters

It often gives the biggest jump in search quality for the least work.

## Common mistake

Reranking too few candidates. If the right text is not in the first pull, no reranker can bring it back.

## Three principles

- **Two passes.** Fast, then careful.
- **Reads pairs.** Question with each result.
- **Short list only.** Too slow for all.

## Related terms

- [Hybrid Search](https://learn.benibix.com/term/ai/hybrid-search)
- [Semantic Search](https://learn.benibix.com/term/ai/semantic-search)
- [Retrieval-Augmented Generation (RAG)](https://learn.benibix.com/term/ai/retrieval-augmented-generation)
- [Cohere](https://learn.benibix.com/term/ai/cohere)
- [Top-k Retrieval](https://learn.benibix.com/term/ai/top-k-retrieval)

## Told apart from

- [Reciprocal Rank Fusion vs Reranking](https://learn.benibix.com/compare/reciprocal-rank-fusion-vs-reranking): People think reciprocal rank fusion is a kind of reranking, and it is not. Fusion merges two or more ranked lists using only each result's place in each list, so it is fast and reads no text. A reranker is a model that reads the question with each result and scores it again. Fusion joins the lists. The reranker then puts the short list in a better order.

![Fifty results from a fast search go into a reranker, which reads the question with each one. The best five come out on top.](https://learn.benibix.com/diagrams/rt-reranking.svg)

---

Source: https://learn.benibix.com/term/ai/reranking
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
