Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI

Lei Y, Ge X, Zhang Y, Yang Y, Ma B (2026)

Publication Type: Conference contribution

Publication year: 2026

Journal

Proceedings of the AAAI Conference on Artificial Intelligence Association for the Advancement of Artificial Intelligence

Publisher: Association for the Advancement of Artificial Intelligence

Book Volume: 40

Pages Range: 579-587

Conference Proceedings Title: Proceedings of the AAAI Conference on Artificial Intelligence

Event location: Singapore, SGP

DOI: 10.1609/aaai.v40i1.37022

Abstract

Understanding whether large language models (LLMs) and the human brain converge on similar computational principles remains a fundamental and important question in cognitive neuroscience and AI. Do the brain-like patterns observed in LLMs emerge simply from scaling, or do they reflect deeper alignment with the architecture of human language processing? This study focuses on the sentence-level neural mechanisms of language models, systematically investigating how layer-wise representations in LLMs align with the dynamic neural responses during human sentence comprehension. By comparing hierarchical embeddings from 14 publicly available LLMs with fMRI data collected from participants, who were exposed to a naturalistic narrative story, we constructed sentence-level neural prediction models to identify the model layers most significantly correlated with brain region activations. Results show that improvements in model performance drive the evolution of representational architectures toward brain-like hierarchies, particularly achieving stronger functional and anatomical correspondence at higher semantic abstraction levels. These findings advance our understanding of the computational parallels between LLMs and the human brain, highlighting the potential of LLMs as models for human language processing.

Involved external institutions

Beijing University of Posts and Telecommunications (BUPT) / 北京邮电大学 CN China (CN) Shandong-University (SDU) CN China (CN) Ludwig-Maximilians-Universität (LMU) DE Germany (DE) Jiangsu Normal University / 江苏师范大学 CN China (CN)

How to cite

APA:

Lei, Y., Ge, X., Zhang, Y., Yang, Y., & Ma, B. (2026). Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI. In Sven Koenig, Chad Jenkins, Matthew E. Taylor (Eds.), Proceedings of the AAAI Conference on Artificial Intelligence (pp. 579-587). Singapore, SGP: Association for the Advancement of Artificial Intelligence.

MLA:

Lei, Yu, et al. "Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI." Proceedings of the 40th AAAI Conference on Artificial Intelligence, AAAI 2026, Singapore, SGP Ed. Sven Koenig, Chad Jenkins, Matthew E. Taylor, Association for the Advancement of Artificial Intelligence, 2026. 579-587.

BibTeX: Download