HN
login
Jev-as-a-Judge: Accept When Confident, Escalate When Unsurearxiv.org

LLM-as-a-judge scales evaluation, but reasoning judges are slow and costly. We study JEV-as-a-Judge: evaluation with JEV, a decision-only judge that returns label probabilities instead of text, and whose confidence…

2 points•nico•about 24 hours ago•0 comments•
#judge#jev#unsure#escalate#accept#confident#evaluation#llm

0 comments

No comments yet.

Related stories