{
  "id": 3904,
  "url": "https://arxiv.org/abs/2605.23032v1",
  "title": "Brain-LLM Alignment Tracks Training Data, Not Typology",
  "summary": "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 ",
  "authors": "Dongxin Guo, Jikun Wu, Siu Ming Yiu",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": "china",
  "published_at": "2026-05-21T20:56:51.000Z",
  "fetched_at": "2026-07-14T16:30:36.741Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3904",
  "original_url": "https://arxiv.org/abs/2605.23032v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}