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

arXiv: https://arxiv.org/abs/2505.22563 · HTML: https://mlsanity.com/paper/2505.22563/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 2 of its 52 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 2 of 2)

- [Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans](https://mlsanity.com/paper/2410.10398/) (2024)
- [fMRI predictors based on language models of increasing complexity recover brain left lateralization](https://mlsanity.com/paper/2405.17992/) (2024)

## Built on by (most cited first, 6 of 6)

- [Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage](https://mlsanity.com/paper/2510.17833/) (2025)
- [Linguistics and Human Brain: A Perspective of Computational Neuroscience](https://mlsanity.com/paper/2602.08275/) (2026)
- [Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning](https://mlsanity.com/paper/2508.10057/) (2025)
- [Limits of Spatial Imagery Reasoning in Frontier LLM Models](https://mlsanity.com/paper/2603.26779/) (2026)
- [Reward Valuation in Large Language Models: Causal Induction of Anhedonia](https://mlsanity.com/paper/2607.06626/) (2026)
- [Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing](https://mlsanity.com/paper/2607.12195/) (2026)

## Abstract (arXiv)

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.