paper-with-me

홈 › Papers

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

2026-09-22 · Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman hf

LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generative and reward-model judges, with blinded human adjudication, we find it within three percentage points of a state-of-the-art LLM judge, our strongest comparator, on ordinary preference and evidence-grounded factuality at 0.36% of the comparator's fee. Larger gaps arise when judgments require checking a derivation or resisting an elaborately written wrong answer. On several benchmarks, JEV's gap to this comparator is concentrated in low-confidence decisions. A frozen cascade that accepts confident verdicts and escalates uncertain ones retains 99% of the comparator's accuracy at lower cost.

📄 PDF Abstract BibTeX arXiv:2609.26550

Code (3)

Promethe-us/awesome-jev ★ 127
Tavish9/awesome-daily-AI-arxiv ★ 121
Valiant-Cat/hfpaper

Similar Papers 제목 키워드 기반

JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification

2026-08-20 · Tianxin Zhou, Ruixi Lin arxiv

Panels of inexpensive LLM judges increasingly make accept-or-escalate decisions. In factuality settings, accepting a claim because several reference-free judges agree can create a hidden risk: agreement may reflect share…

Towards Expert Financial QA via Self-Improving RAG

2026-08-27 · Junjie Xiong, Shawheen Ghezavat, Aum Hirpara arxiv

Expert-level financial question answering requires both grounded verification to catch numeric hallucinations and audit trails for regulatory compliance, attributes that standard single-pass RAG systems lack. We take a s…

Question Answering

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

2024-07-25 · JaeHun Jung, Faeze Brahman, Yejin Choi

We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncritically rely on model preferences for pair…

Chatbot

Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees

2026-08-18 · Sher Badshah, Ali Emami, Hassan Sajjad arxiv

Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference …

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

2026-06-25 · Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana, Ammar Abbas 외 arxiv

Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive for easy queries or insufficient for har…