Do brains and language models converge toward the same internal representations of the world? Recent years have seen a rise in studies of neural activations and model alignment. In this work, we review 25 fMRI-based studies published between 2023 and 2025 and explicitly confront their findings with two key hypotheses: (i) the Platonic Representation Hypothesis -- that as models scale and improve, they converge to a representation of the real world, and (ii) the Intermediate-Layer Advantage -- that intermediate (mid-depth) layers often encode richer, more generalizable features. Our findings provide converging evidence that models and brains may share abstract representational structures, supporting both hypotheses and motivating further research on brain-model alignment.
@article{arxiv.2510.17833,
title = {Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage},
author = {Ángela López-Cardona and Sebastián Idesis and Mireia Masias-Bruns and Sergi Abadal and Ioannis Arapakis},
journal= {arXiv preprint arXiv:2510.17833},
year = {2025}
}