PulseAugur
中
实时 09:43:31
English(EN) Local Support Learning

新的本地支持学习框架解决了大型语言模型中的灾难性遗忘问题

研究人员开发了本地支持学习(LSL),一个旨在解决预训练大型模型中灾难性遗忘问题的新颖框架。LSL 将遗忘视为权重矩阵输入空间中的一个几何问题来解决,并提出了一种改进标准基于梯度的优化器的保留目标。该框架集成了带有门控功能的权重适配器,该适配器经过训练,仅激活来自其特定训练分布的输入,从而实现本地化更新。该方法已成功解决了多达 70 亿参数的大型语言模型中的遗忘问题,在多个训练阶段以高效的内存和计算使用量保留了预训练和微调的能力。 AI

影响 这个新框架可以实现更高效、更持续的大型语言模型学习,减少广泛重新训练的需求。

排序理由 详细介绍大型语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

新的本地支持学习框架解决了大型语言模型中的灾难性遗忘问题

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍大型语言模型新方法的学术论文。[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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Assaf Ben-Kish, Akarsh Kumar, James Glass, Raja Giryes ·

    本地支持学习

    arXiv:2610.02126v1 Announce Type: cross Abstract: We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix, we uncover a natural retention objective under which updates…