arXiv 2610.21046 · cs.CL · 2026-10-15
PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews
Dingjie Song, Zhiling Yan, Ziqian Zhang, Yuxuan Zhang, Lichao Sun
机构待核实
在最新榜 #26 2026-W43 第 1 名（进行中） 本站收录于 2026-10-21
一句话要点
ReviewFact 标注审稿意见中的事实错误，PremiseCheck 结合大模型和轻量判别模型低成本核查。
ReviewFact labels factual errors in peer reviews; PremiseCheck combines an LLM with cheap decision models to verify them efficiently.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：评测与数据
- 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
- Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers ▲63
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。