Unverified50% confidenceFactExact time
In sentence-transformers, the model encodes a sentence into a fixed-dimension vector (such as 384 or 768 dimensions), and sentences with similar semantics are closer together in vector space.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
Unverified现代嵌入模型（如sentence-transformers系列）通常输出768维或1536维的向量79% similarVerifiedSemantically similar texts are also close in distance within vector space, which is the mathematical foundation of vector retrieval.73% similarUnverifiedThe vector input to the model equals the word embedding plus the positional embedding; for example, 7 characters generate 7 word embeddings and 7 positional embeddings that are added together to produce the actual input72% similarUnverifiedEmbedding models do not output text; they only convert inputs into vectors, whose meaning lies in their relative relationships to one another (the embedding space).70% similarUnverifiedInside an LLM, the input word sequence is converted into a sequence of high-dimensional vectors, and the relationships between words are encoded by the geometric relationships of the vectors (distance, direction, projection).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1080371API
curl https://kongchang.com/api/v1/knowledge/claims/1080371MCP
get_claim(id=1080371)