aiqbench analysis
This study demonstrates that despite linguistic differences, the human brain encodes semantic meaning in a consistent geometric structure across languages and individuals. By decoding neural activity from 227 participants speaking Chinese, English, and French, researchers identified a shared cortical semantic geometry that aligns with known functional gradients in the brain. This work advances fundamental machine learning by revealing the biological constraints underlying cross-lingual representation learning and generalization.
Multilingual Brain Decoding Reveals Shared Cortical Semantic Geometry
arXiv:2610.26927v1 Announce Type: cross Abstract: Human languages differ markedly in lexical and syntactic form yet can convey similar semantic content. The neural basis of this cross-language semantic commonality remains unclear. Here we developed a multilingual brain decoding framework and analysed brain recordings from 227 participants spanning Chinese, English and French. We found that cortical semantic representations exhibited consistent semantic geometry relationships across languages and individuals, revealing a shared cortical semantic geometry. Importantly, the cross-language consistency of cortical semantic geometry increased from sensorimotor to higher-order association cortex, forming a shared semantic geometry gradient closely aligned with the principal cortical functional gradient. Our work establishes generalizable multilingual brain decoding and identifies stable cortical semantic geometry as a neural basis for semantic commonality across languages.
Abstract:Human languages differ markedly in lexical and syntactic form yet can convey similar semantic content. The neural basis of this cross-language semantic commonality remains unclear. Here we developed a multilingual brain decoding framework and analysed brain recordings from 227 participants spanning Chinese, English and French. We found that cortical semantic representations exhibited consistent semantic geometry relationships across languages and individuals, revealing a shared cortical semantic geometry. Importantly, the cross-language consistency of cortical semantic geometry increased from sensorimotor to higher-order association cortex, forming a shared semantic geometry gradient closely aligned with the principal cortical functional gradient. Our work establishes generalizable multilingual brain decoding and identifies stable cortical semantic geometry as a neural basis for semantic commonality across languages.
Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI)
arXiv:2610.26927 [q-bio.NC]
(or arXiv:2610.26927v1 [q-bio.NC] for this version)
https://doi.org/10.48550/arXiv.2610.26927 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 213 words
Related coverage
Speculative Decoding and the Curse of Multilinguality
arXiv · Aug 6, 2026
Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap
arXiv · Sep 1, 2026
Whisfusion: Parallel ASR Decoding with Masked Diffusion
arXiv · Jun 10, 2026
Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual Translation
arXiv · Oct 16, 2026