Verified65% confidenceFactExact time
Reranking uses a cross-encoder to score query-document pairs one by one, with accuracy far higher than vector similarity but at higher computational cost, so fine ranking is done only on the small number of candidates after coarse ranking, forming a two-stage architecture of coarse ranking plus fine ranking.
3
Sources
65%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedReranking is typically implemented using cross-encoders, which concatenate the query and candidate documents before feeding them in together; it usually reranks only the Top-50 to Top-100 candidates and finally selects Top-3 to Top-5 to pass to the generative model.80% similarUnverifiedA Cross-Encoder concatenates the query and candidate code snippet before feeding them together as input, achieving higher scoring accuracy than a Bi-Encoder but at greater computational cost, so it is typically used only to re-rank the Top-K candidates recalled by ANN.78% similarUnverified重排阶段通常对10-50条候选文档进行精排，能够捕捉双编码器遗漏的细微语义关联从而提升检索相关性76% similarUnverifiedThe standard approach is to use the cross-encoder only to rerank the dozens of candidates returned by retrieval, forming a two-stage pipeline of "coarse recall + fine ranking".76% similarUnverifiedThe computational complexity of cross-encoders is O(n²); document representations cannot be precomputed and scoring must be done online pair by pair, so cross-encoders are typically only used to rerank the top-k results returned by an initial retrieval stage.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1020535API
curl https://kongchang.com/api/v1/knowledge/claims/1020535MCP
get_claim(id=1020535)