Verified80% confidenceFactTime unknown
Commonly used Rerank models include Cohere Rerank and BGE-Reranker.
8
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReranker模型（如Cohere Rerank、BGE-Reranker、bce-reranker）同时考虑Query和Document的交互信息，排序精度更高但计算成本也更大74% similarUnverifiedCommonly used open-source reranking models include the BGE-Reranker series and models released by BAAI.70% similarVerifiedReranking is the process of using a fine-ranking model to re-score and re-sort candidate segments after an initial Top-K retrieval, in order to improve the quality of the context fed into the large model.67% similarVerifiedReranking uses a Cross-Encoder model to re-score and re-rank the candidate chunks recalled by Top-K, with precision far higher than that of a Bi-Encoder.64% similarUnverifiedRebasing causes the numerical scores output by the model on the same input to drift, so it is necessary to track the correspondence between model version numbers and thresholds.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18817API
curl https://kongchang.com/api/v1/knowledge/claims/18817MCP
get_claim(id=18817)