AI ethics evidence index Search
Source-linked daily record
Evidence record 3904 · automatically gathered

Brain-LLM Alignment Tracks Training Data, Not Typology

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

Record details

Published: 21 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Safety & alignment

Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography

arXiv · 21 May 2026

Same publisher byline · Shared topic: Safety & alignment

EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent

arXiv · 10 May 2026

Same publisher byline · Shared topic: Safety & alignment

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

arXiv · 20 April 2026

Same publisher byline

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

arXiv · 1 May 2026

Shared topic: Safety & alignment · Same region: China

AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task

arXiv · 2 June 2026

Shared topic: Safety & alignment · Same region: China

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv · 13 June 2026

How to cite this record

ethics.ai (21 May 2026), “Brain-LLM Alignment Tracks Training Data, Not Typology,” evidence record 3904, https://ethics.ai/record/3904 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.