๐Ÿ“–
Language Impairment as a Lens onto Large Language Models
Muxuan He, Wang Bill Zhu, Yue Chen, Elsi Kaiser, Weizhi Du, Yao Du, Samuel Nastase, Yanjun Gao

Language Impairment as a Lens onto Large Language Models

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

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 analogous to the human language system, by introducing a novel mechanistic interpretability framework inspired by aphasia. Through two complementary approaches, classifier-guided lesioning and continuous activation steering, we systematically induce aphasia-like breakdowns in LLMs. We find that language functions can be successfully isolated to discrete structural circuits and continuous representational vectors, yet these functions remain densely entangled with significant circuit overlap and vector similarities across distinct aphasic profiles. Furthermore, while steering generalizes robustly across downstream tasks, structural lesioning remains asymmetrically constrained. By bridging neuropsychology and mechanistic interpretability, we demonstrate that LLMs, functionally analogous to biological brains, rely on a densely entangled architecture that can be systematically mapped through clinically-informed interventions.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title Language Impairment as a Lens onto Large Language Models
Author / Organization Muxuan He, Wang Bill Zhu, Yue Chen, Elsi Kaiser, Weizhi Du, Yao Du, Samuel Nastase, Yanjun Gao
Subject & Discipline cs.CL
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-268965
Original Source Link Visit Source Page on arxiv.org »