# Reranking

A precision second pass that reorders an over-fetched candidate set so the most relevant chunks land in the prompt.

## Why the CCAR-P exam tests this

Reranking is the standard fix for 'right doc retrieved but buried,' and P3 expects you to place it correctly in the retrieval stack.

## Definition

**Reranking** is a two-stage retrieval pattern. Stage one uses a fast, cheap retriever (vector and/or keyword) to fetch a **wide candidate set** — say top-50. Stage two applies a slower, more accurate **reranker** (typically a cross-encoder that scores the query and each candidate jointly) to reorder them, and you keep the top few (say top-5) for the prompt.

The payoff is **precision**: bi-encoder vector search embeds query and document separately and can miss fine-grained relevance, while a cross-encoder reads them together and judges actual match quality. This directly lifts the answer because LLMs weight earlier/most-relevant context more heavily and the prompt has limited room.

The cost is **latency and compute** per candidate, so you rerank a bounded candidate set, not the whole corpus. Reranking improves ordering; it cannot recover a relevant document that stage-one retrieval never returned — fix recall first, then precision.

## Exam trap

Reranking only reorders candidates it was given — if the first-stage retriever missed the right chunk, no reranker can surface it, so it is not a cure for low recall.

## Commonly confused with

- **hybrid-retrieval** — Hybrid retrieval widens/improves the candidate set (recall); reranking sharpens its order (precision). Often used together.
- **chunking-strategy** — Reranking scores existing chunks; it does not change how documents were split.

## Related

- rag-pipeline
- hybrid-retrieval
- chunking-strategy

---

Source: Claude Cert Prep — an independent, unofficial CCAR-P study resource (domain P3). Not affiliated with Anthropic.