Language Impairment as a Lens onto Large Language Models
arXiv:2610.28992v1 Announce Type: new Abstract: 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 theo…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.CL
Language Impairment as a Lens onto Large Language Models