[KongchangAI]
Unverified50% confidenceFactExact time

研究表明LLM裁判倾向于偏好语气自信、篇幅较长或风格与自身相似的输出,且对越狱式措辞更为宽容

1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/931084
API
curl https://kongchang.com/api/v1/knowledge/claims/931084
MCP
get_claim(id=931084)