protologue

Reranking

Also called re-ranking, cross-encoder reranking, reranker.

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.

Sources

  1. Nogueira and Cho (2019). Passage Re-ranking with BERT.

Cite this entry

Protologue. (2026). Reranking. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0129). https://protologue.com/t/reranking/

BibTeX
@misc{protologue_reranking,
  title = {Reranking},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0129},
  url = {https://protologue.com/t/reranking/}
}

Markdown JSON