CLAIJan 27

Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes

arXiv:2601.19723v11 citationsh-index: 17
Originality Incremental advance
AI Analysis

This work addresses the need for scalable computational proxies to study aphasia and language cognition, offering a controlled framework for testing rehabilitation hypotheses, though it is incremental in applying existing methods to a new clinical domain.

The researchers tackled the problem of simulating aphasia language impairments by selectively perturbing components in large language models, finding that targeted perturbations yield more systematic aphasia-like regressions than random ones, with modular models providing better mappings.

Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to reproduce language-production impairments characteristic of aphasia following focal brain lesions. Such models could provide scalable proxies for testing rehabilitation hypotheses, and offer a controlled framework for probing the functional organization of language. We introduce a clinically grounded, component-level framework that simulates aphasia by selectively perturbing functional components in LLMs, and apply it to both modular Mixture-of-Experts models and dense Transformers using a unified intervention interface. Our pipeline (i) identifies subtype-linked components for Broca's and Wernicke's aphasia, (ii) interprets these components with linguistic probing tasks, and (iii) induces graded impairments by progressively perturbing the top-k subtype-linked components, evaluating outcomes with Western Aphasia Battery (WAB) subtests summarized by Aphasia Quotient (AQ). Across architectures and lesioning strategies, subtype-targeted perturbations yield more systematic, aphasia-like regressions than size-matched random perturbations, and MoE modularity supports more localized and interpretable phenotype-to-component mappings. These findings suggest that modular LLMs, combined with clinically informed component perturbations, provide a promising platform for simulating aphasic language production and studying how distinct language functions degrade under targeted disruptions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes