Unverified50% confidenceFactExact time
When small-parameter models produce structured output, the attention mechanism is more easily drawn to natural-language labels that appear repeatedly or in prominent positions in the prompt, while relatively ignoring the enum definitions in the Schema.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA model can avoid words or sentence patterns flagged as harmful at the surface output level while retaining the original bias structure in the semantic associations encoded in its weights.70% similarUnverifiedLarge language models are highly sensitive to the wording, format, number of examples and even punctuation of prompts, and different phrasings of the same task may produce significant score fluctuations.70% similarUnverified大语言模型通过注意力机制（Attention Mechanism）对上下文窗口内所有token同时计算相关性权重，而非像人类一样逐步阅读和筛选资料70% 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）69% similarUnverifiedDeduplication is a prerequisite for the scoring mechanism; the same request may appear with different wording across multiple chat records, and AI handles semantic aggregation rather than keyword matching.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070988API
curl https://kongchang.com/api/v1/knowledge/claims/1070988MCP
get_claim(id=1070988)