Unverified50% confidenceFactExact time
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）
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Seedream 5.0 Pro深度实测：中文绘图能力全面解析
bilibili碳基生物退役指南7/9/2026
Related Claims
Unverified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70% similarUnverifiedThe summarization capability of large language models is essentially the process of identifying key semantic nodes in text through the attention mechanism, compressing long documents into short texts that retain the core arguments.68% similarUnverified大语言模型的执行层通过 Function Calling（工具调用）机制将 LLM 的文本输出转化为对真实系统的操作指令67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488160API
curl https://kongchang.com/api/v1/knowledge/claims/488160MCP
get_claim(id=488160)