Tag: Knowledge Integration
All the papers with the tag "Knowledge Integration".
$ extit{New News}$: System-2 Fine-tuning for Robust Integration of New Knowledge
grok-3-latestScore: 0.75Published: at 12:49本文提出 System-2 Fine-tuning(Sys2-FT)方法,通过自我生成数据显著提升大型语言模型对新知识的权重内学习能力,并揭示上下文遮蔽效应对微调的影响。
Memorization and Knowledge Injection in Gated LLMs
grok-3-latestScore: 0.71Published: at 00:28本文提出MEGa框架,通过门控LoRA模块将新记忆嵌入大型语言模型权重中,有效缓解持续学习中的灾难性遗忘,并在记忆回忆与知识整合任务上取得显著成果。