{
  "id": "reranking",
  "code": "PTL-0129",
  "term": "Reranking",
  "aliases": [
    "re-ranking",
    "cross-encoder reranking",
    "reranker"
  ],
  "category": "retrieval-tools",
  "definition": "Reranking is a second retrieval stage in which a more accurate but slower model, typically a cross-encoder that reads the query and each candidate together, rescores the top results from a fast first-stage search and reorders them.",
  "description": "First-stage retrievers embed queries and documents separately to stay fast, which limits accuracy. A reranker sees both texts jointly, so it judges relevance more precisely, and applying it only to a few dozen candidates keeps cost manageable. Rerankers can also be LLMs prompted to judge or order passages.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "dense-retrieval",
    "hybrid-search",
    "colbert",
    "retrieval-augmented-generation"
  ],
  "introduced": 2019,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Passage Re-ranking with BERT",
      "authors": "Nogueira and Cho",
      "year": 2019,
      "url": "https://arxiv.org/abs/1901.04085"
    }
  ],
  "url": "https://protologue.com/t/reranking/",
  "citation": "Protologue. (2026). Reranking. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0129). https://protologue.com/t/reranking/"
}