Verified90% confidenceFactTime unknown
The LLM-as-Judge method uses large language models such as GPT-4 as judges to automatically score the output quality of Agents.
9
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM-as-Judge范式使用能力更强的大语言模型（如GPT-4o或Claude 3.5 Sonnet）对被评估模型的输出进行打分83% similarUnverifiedLLM-as-Judge使用另一个强力模型（如GPT-4）来评判输出质量，因其灵活性正在成为主流评估方式82% similarUnverifiedGPT-4等模型在作为评判者时会系统性地偏好特定位置的回答79% similarUnverifiedThe evaluation adopted a hybrid approach using GPT-5.5 as the LLM judge alongside human taste scoring.78% similarUnverifiedWhen a GPT-4-level model acts as a Judge, its evaluation results agree with human experts more than 80% of the time.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24751API
curl https://kongchang.com/api/v1/knowledge/claims/24751MCP
get_claim(id=24751)