How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identifi... Activation: brain, fmri, multilingual, lesion
Scanned 9/11/2026
Install to Claude Code
npx -y skills add hiyenwong/ai_collection --skill computational-lesions-multilingual-language-models-separate- --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Computational Lesions Multilingual Language Models Separate?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-computational-lesions-multilingual-language-models-e6b5cb02)More formats (shields.io, HTML) on the badges page.
---
name: computational-lesions-multilingual-language-models-separate-
description: "How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identifi... Activation: brain, fmri, multilingual, lesion"
---
# Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
## Overview
How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions across languages, but it cannot by itself show whether the underlying processing is shared or language-specific. Here we use six multilingual large language models (LLMs) as controllable systems and create targeted ``computational lesions'' by zeroing small parameter sets that are important across languages or especially important for one language. We then compare intact and lesioned models in predicting functional magnetic resonance imaging (fMRI) responses during 100 minutes of naturalistic story listening in native English, Chinese and French (112 participants). Lesioning a
## Source Paper
- **Title:** Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
- **Authors:** Yang Cui, Jingyuan Sun, Yizheng Sun et al.
- **arXiv:** 2604.10627v1
- **Published:** 2026-04-12
- **Categories:** cs.CL, cs.AI, cs.CE
- **PDF:** https://arxiv.org/pdf/2604.10627v1
## Key Contributions
1. Theoretical analysis and formal framework
## Core Concepts
### Key Methodology
These results support a shared backbone with embedded specializations and provide a causal framework for studying multilingual brain-model alignment.
### Technical Details
These results support a shared backbone with embedded specializations and provide a causal framework for studying multilingual brain-model alignment.
## Practical Applications
- Multilingual language model analysis
- Brain-language alignment research
- Brain signal decoding
- Neuroimaging analysis
## Related Work
Related skills and approaches in the domain.
## Activation Keywords
- brain
- fmri
- multilingual
- lesion
## Notes
This skill was created from arXiv paper 2604.10627v1 as part of automated neuroscience research workflow.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!