Task Context Shapes Component Roles in Language Models
arXiv:2610.13895v1 Announce Type: cross Abstract: 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 of language-model computation. Here, we compare fixed model components across tasks using identical graph facts, statements specifying which directed connections are pres…