Preprint
Oct 2026
Language Impairment as a Lens onto Large Language Models
Although large language models (LLMs) encode language in highly distributed spaces, they remain vulnerable to focal disruptions---a phenomenon strikingly similar to how localized brain damage causes clinical aphasia in humans. To investigate this theoretical tension, we ask whether LLMs possess a functional structure a...
Mu-Xuan He, Wang Bill Zhu, Yue-Ying Chen et al.
· 0 citations