A fast retriever first gathers a manageable candidate set. A cross-encoder, late-interaction model, or task-specific scorer then evaluates each candidate against the query with richer interactions.
Reranking applies a more precise scoring method to reorder candidates produced by an initial retrieval step.
A fast retriever first gathers a manageable candidate set. A cross-encoder, late-interaction model, or task-specific scorer then evaluates each candidate against the query with richer interactions.