Unverified50% confidenceTradeoffExact time
A 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReranking uses a Cross-Encoder model to score candidate documents retrieved in the initial retrieval pairwise, then fine-ranks the Top-K to feed into the LLM.77% similarVerified重排序（Re-ranking）机制在初步检索后引入交叉编码器（Cross-Encoder）对候选文档重新打分，提升输入大模型的上下文质量75% similarUnverifiedReranking 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.72% 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.70% similarUnverified生产系统通常采用粗召回+精排的两阶段架构：Bi-Encoder召回Top20-50候选，Cross-Encoder重排后取Top3-5送入大模型66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/974953API
curl https://kongchang.com/api/v1/knowledge/claims/974953MCP
get_claim(id=974953)