Unverified50% confidenceCautionExact time
Once a knowledge base is created, the embedding model cannot be replaced without rebuilding the knowledge base, because the vector spaces generated by different models are not interchangeable.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRAG的知识存储在外部索引中，模型本身并未内化这些信息，无法进行推理组合、技能迁移或形成新的概念抽象72% similarUnverified大模型的指令与数据共享同一个输入上下文窗口，无法建立物理隔离边界，这是架构层面的根本性挑战而非微调可解决70% similarUnverifiedThis paper finds that modifying only the storage layers may be insufficient to fundamentally alter model output behavior; intervention in the intermediate layers responsible for information routing is also required, otherwise knowledge editing may fail.67% similarUnverified更换或升级嵌入模型时，旧向量与新向量处于不同语义空间无法直接比较，往往需要全量重建索引64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985373API
curl https://kongchang.com/api/v1/knowledge/claims/985373MCP
get_claim(id=985373)