PulseAugur
中
实时 13:29:31
English(EN) HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

新的 HLE-Verified 基准修正了 Humanity's Last Exam 中的错误

研究人员开发了 HLE-Verified,这是 Humanity's Last Exam (HLE) 基准的一个修订版本,旨在解决有关噪声数据和有偏评估的担忧。新基准采用两阶段验证和修复过程,包括专家审查和基于模型的交叉检查,以确保准确性。在测试最先进的语言模型时,HLE-Verified 显示平均准确率提高了 7-10 个百分点,在包含原始问题陈述或答案错误的条目上有了显著改进。 AI

影响 通过减少基准数据集中的噪声和错误,提高了 LLM 评估的可靠性。

排序理由 该条目是一篇研究论文,详细介绍了用于评估 LLM 的新基准。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的 HLE-Verified 基准修正了 Humanity's Last Exam 中的错误

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该条目是一篇研究论文,详细介绍了用于评估 LLM 的新基准。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
51 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Weiqi Zhai, Zhihai Wang, Jinghang Wang, Boyu Yang, Xiaogang Li, Xander Xu, Bohan Wang, Peng Wang, Xingzhe Wu, Anfeng Li, Qiyuan Feng, Yuhao Zhou, Taolin Han, Wenjie Luo, Yiyuan Li, Xiang Zheng, Yaxuan Wang, Ruixiang Luo, Guojie Lin, Peiyao Xiao, Chenglia… ·

    HLE-Verified:人类最后一次考试的系统性验证与结构化修订

    arXiv:2602.13964v4 Announce Type: replace Abstract: Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However, community-led analyses have raised concerns that HLE contains a non-tri…