Aller au contenu
Atlas de l'IA

Réordonnancement des résultats

Réordonner les candidats selon leur pertinence réelle

Langage et connaissancesIntermédiaire #10
entréeTexteTableau

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

Takes a query and a short list of recalled candidates, and returns a reordered ranking with relevance scores. Its division of labour differs from embedding retrieval: retrieval uses cheap vector neighbours to pull dozens from tens of thousands, whereas reranking applies a costlier model to score those dozens carefully, so it only runs over the candidate set.

Comment c'est fait

The typical approach is a cross-encoder: query and candidate are concatenated into one sequence and a single model outputs a relevance score; seeing both at once is more accurate than two-tower encoders, but it cannot be pre-computed and must run per pair. To control latency, a common pattern truncates with a small model first and reranks with a larger one — or simply prompts a large model to score.

Produits représentatifs

4

Organisations concernées

Usages typiques

  • Improving evidence quality after RAG retrieval
  • Final ranking in e-commerce and content search
  • Selecting the most relevant passages for a QA system
  • Deduplicating and choosing among candidate answers

Comment on l'évalue

nDCG@k
Discounted gain in the top-k after reranking, rewarding better placement
MAP
Mean of average precision over all relevant items
MRR
Quality of the position of the first relevant result

Limites et points difficiles

  • Cross-encoders score each candidate separately, so latency climbs steeply with candidate count
  • Judgements are unstable on out-of-distribution queries, and truncating long documents causes errors
  • It can only reorder what was recalled; anything retrieval missed cannot be recovered

Concepts sous-jacents