arXiv 2609.26550 · cs.AI · 2026-09-22
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman
Carnegie Mellon University
在最新榜 #105 本站收录于 2026-10-21
一句话要点
用只做决策的轻量评审模型做第一轮打分，没把握时再升级给大模型，成本仅为后者的零头。
Uses a decision-only judge as a cheap first pass and escalates to stronger judges only when unsure.
阅读 arXiv 原文 PDF Hugging Face 讨论 项目页
主题与学科
同主题：评测与数据
- PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews ▲727
- OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners ▲291
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations ▲287
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay ▲73
- More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models ▲65
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。