Brain-LLM Alignment Tracks Training Data, Not Typology
For cognitive neuroscience and NLP, this work clarifies that apparent English advantages in brain-LLM alignment are artifacts of training data, revealing genuine typological structure in syntactic processing.
Brain-LLM alignment generalizes cross-linguistically, but training-language dominance, not English-specific properties, drives alignment patterns; a Chinese-dominant model reverses the gradient, and typological distance independently degrades alignment, with syntax-associated regions showing 2.3× steeper gradients and tokenization fertility explaining ~60% of cross-linguistic encoding layer shifts.
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.