Brain-LLM Alignment Tracks Training Data, Not Typology

A study of fMRI data from 112 English, Chinese, and French speakers found that brain-LLM alignment is driven by training-language dominance, not an inherent property of English. A Chinese-dominant model reversed the alignment gradient entirely, matching Chinese brains best and English worst, while formal typological distance independently degraded alignment, particularly in syntax-associated brain regions. The findings reveal that the apparent "English advantage" is an artifact of training data composition, with remaining variation reflecting genuine typological structure in syntactic processing.

arXiv:2605.23032v1 Announce Type: new Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using fMRI data from 112 participants across English, Chinese, and French the Le Petit Prince corpus and seven LLMs spanning English-dominant, Chinese-dominant, and multilingual architectures. Our central finding is that training-language dominance, not an inherent property of English, drives the alignment pattern: a Chinese-dominant model Baichuan2-7B , architecture-matched to LLaMA-2-7B, reverses the gradient entirely, aligning best with Chinese brains and worst with English. Beyond training dominance, formal typological distance independently covaries with alignment degradation, syntax-associated brain regions IFG show $2.3\times$ steeper typological gradients than lexico-semantic regions PTL , and tokenization fertility accounts for $\sim$60% of a cross-linguistic shift in optimal encoding layer. These results reveal that the apparent "English advantage" in brain-LLM alignment is an artifact of training data composition, while the remaining variation reflects genuine typological structure concentrated in syntactic processing.