[KongchangAI]
Unverified50% confidenceSolutionExact time

对大语言模型而言,「不要做X」的负向约束有时比「要做Y」的正向指令更有效,因为负样本相当于在概率空间中设置了禁区

1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/575492
API
curl https://kongchang.com/api/v1/knowledge/claims/575492
MCP
get_claim(id=575492)