站内快照 · 国内可打开。外网原文可能无法访问。

• 论文公开站arXiv2026年10月12日 2:17

  Task Context Shapes Component Roles in Language Models

  Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain regions, which motivate a network view o

  原文链接