[KongchangAI]
Unverified60% confidenceFactExact time

LLM as Judge由Lianmin Zheng等人在MT-Bench论文(2023)中系统提出,核心思路是用独立大语言模型对另一模型输出进行打分以替代人工标注

2
Sources
60%
Confidence
Long-term
Relevance
7/7/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/170755
API
curl https://kongchang.com/api/v1/knowledge/claims/170755
MCP
get_claim(id=170755)