Unverified50% confidenceFactExact time
提示词注入分为直接注入和间接注入两种形式，因语言模型无法区分数据与指令，凡进入上下文窗口的文本都可能被执行
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
VerifiedThe root cause of Prompt Injection is that large models cannot structurally distinguish between "system instructions" and "user data," as both are presented as natural language text at input time.83% similarUnverifiedText embedding technology has followed a development path from Word2Vec and Sentence-BERT to general-purpose embedding models based on instruction fine-tuning.72% similarUnverified工具调用的参数通过与普通文本输出不同的结构化通道传递，可能经过不同的后处理管道，从而绕过针对对话内容设计的CoT过滤层70% similarUnverifiedEarly embedding models like Word2Vec and GloVe could only handle word-level representations, while modern models can encode entire sentences or paragraphs70% similarUnverified前沿绘图模型内部通常搭配小型语言模型对用户输入进行语义理解和扩展补全，该机制被称为提示词扩展（Prompt Expansion）70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573093API
curl https://kongchang.com/api/v1/knowledge/claims/573093MCP
get_claim(id=573093)