English(EN) Measuring all the noises of LLM Evals

新研究量化LLM评估中的噪声

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-14 04:00

arXiv上的一篇新论文介绍了一种衡量大型语言模型（LLM）评估中各种噪声来源的方法。该研究确定了三种类型的噪声：模型输出变化带来的预测噪声、问题采样带来的数据噪声以及它们的总噪声。为了提高统计功效和相对比较，作者提出了一种“全对比较”方法，该方法分析了大量评估中的数百万次预测。 AI

影响提供了一个更具统计学鲁棒性的LLM评估框架，可能带来更可靠的模型比较。

排序理由学术论文发布在arXiv上，详细介绍了一种新的LLM评估方法。 [lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文发布在arXiv上，详细介绍了一种新的LLM评估方法。 [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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv stat.ML TIER_1 English(EN) · Sida I. Wang · 2026-10-14 04:00

衡量LLM评估中的所有噪音

arXiv:2512.21326v3 Announce Type: replace-cross Abstract: Applying well-established statistical methods effectively to LLM evals requires consideration of model correlations and prediction noises. Leading evals often ignore data noise, have low statistical power, or make unnecess…