Unverified50% confidenceFactExact time
现代Sentence Embedding模型通常采用双塔（Bi-Encoder）结构，查询和文档分别独立编码为向量
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
UnverifiedA Bi-Encoder encodes queries and documents independently into vectors and computes relevance via cosine similarity or dot product; document vectors can be pre-computed offline and stored in a vector database.84% 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79% similarUnverified嵌入模型采用双塔（Bi-encoder）架构，将查询和文档独立编码成向量，然后通过余弦相似度等方式计算距离77% similarUnverified主流Embedding模型（如BGE、text-embedding系列）通常基于BERT架构的编码器（Encoder-only），通过对比学习让语义相近的句子在向量空间中靠拢；而GPT类生成模型基于解码器（Decoder-only）76% similarUnverifiedRetrieval BERT uses a Bi-Encoder (dual-tower model), where two sentences each generate a vector and similarity is then computed; vectors can be precomputed offline, enabling fast online matching.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488689API
curl https://kongchang.com/api/v1/knowledge/claims/488689MCP
get_claim(id=488689)