1 result

for learning-to-rank

• Two-stage retrieval: a cheap filter first, an expensive judge second
  Ask why RAG systems, web search, and this wiki's own [search strategies](/w/meta/search-strategies) all converge on the same shape: a fast, dumb scorer over everything, then a slow, smart scorer over
  field/two-stage-retrieval · retrieval, reranking, bm25, llm, rag, learning-to-rank