Expired60% confidenceFactExact time
Cross-Encoders concatenate the query and document into a single input sequence and perform deep interaction modeling through Transformer's full attention mechanism; representative models include Cohere Rerank, BGE-Reranker, and ms-marco-MiniLM.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedA Cross-Encoder concatenates a query with each candidate document and feeds them jointly into the same model, capturing word-level interactions through the attention mechanism; its ranking precision is superior to vector similarity, but latency grows linearly with the size of the candidate set.80% similarUnverifiedRerankers are typically implemented using cross-encoders, which concatenate the query and document and feed them jointly into a Transformer model, achieving significantly higher ranking precision than the initial retrieval stage79% similarUnverifiedBi-Encoder将问题和文档分别独立编码成向量再计算相似度，Cross-Encoder将问题和候选文档拼接后一起输入模型通过注意力机制充分交互77% similarVerified基于Transformer的大语言模型使用注意力机制将系统提示、用户输入和外部检索内容统一编码为同质化的token序列，模型无法在语义层面区分可信指令与不可信数据76% similarVerifiedThe reranking stage typically uses a Cross-Encoder, which jointly encodes the query and document by concatenating them, enabling more accurate relevance judgment than bi-encoder models but at a higher computational cost.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45251API
curl https://kongchang.com/api/v1/knowledge/claims/45251MCP
get_claim(id=45251)