Unverified50% confidenceFactExact time
Representative works of the "LLM-as-a-judge" paradigm include MT-Bench/Chatbot Arena by Zheng et al., who found that GPT-4 as a judge achieves over 80% agreement with human preferences.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedWhen a GPT-4-level model acts as a Judge, its evaluation results agree with human experts more than 80% of the time.75% similarUnverified研究表明GPT-4作为评估者与人类专家评分的一致性超过80%，显著高于BLEU、ROUGE等基于词汇匹配的自动化指标68% similarVerifiedThe LLM-as-Judge method uses large language models such as GPT-4 as judges to automatically score the output quality of Agents.68% 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66% 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66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907809API
curl https://kongchang.com/api/v1/knowledge/claims/907809MCP
get_claim(id=907809)