English(EN) Revisiting the Past: Data Unlearning with Model State History

新的MSA算法利用模型历史高效地从LLM中遗忘数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-29 04:00

研究人员推出了一种名为模型状态算术（MSA）的新型算法，旨在高效地从大型语言模型中移除特定数据点的影响。与计算上不可行的完全重新训练不同，MSA利用历史模型检查点来抵消不需要的数据的影响。实验表明，MSA在各种基准测试和模型上表现具有竞争力，并且通常优于现有的数据遗忘方法。 AI

影响为LLM中的数据擦除提供了一种更有效的方法，有可能提高模型的灵活性并遵守数据隐私法规。

排序理由这是一篇详细介绍大型语言模型中数据遗忘新算法的研究论文。

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 这是一篇详细介绍大型语言模型中数据遗忘新算法的研究论文。
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, safety; 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: 162 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。

arXiv cs.LG TIER_1 English(EN) · Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi · 2026-04-29 04:00

重温过去：通过模型状态历史进行数据遗忘

arXiv:2506.20941v3 Announce Type: replace Abstract: Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of such proble…