English(EN) What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models

新研究追踪语言模型在预训练期间的知识获取

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

一篇新的研究论文通过分析在不同年份的网络快照上训练的模型，探讨了语言模型在预训练期间如何获取知识。研究人员开发了一种时间变异性得分（TVS）来衡量网络文本中知识的普遍性如何随时间变化。他们的发现表明，时间变异性越高的条目在预训练后期学习得越有效，并能在知识密集型任务上带来更好的表现。 AI

影响为理解语言模型如何随时间学习和表征知识提供了一种新的诊断方法。

排序理由发表在arXiv上的研究论文，详细介绍了一种分析模型预训练的新方法。[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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发表在arXiv上的研究论文，详细介绍了一种分析模型预训练的新方法。[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, model release; 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 cs.AI TIER_1 English(EN) · Chang Su, Bin Wu, Emine Yilmaz, Yao Lu · 2026-10-28 04:00

预训练期间知识如何提升？使用即时模型追踪知识获取

arXiv:2610.37631v1 Announce Type: new Abstract: Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-…