Scaling and context steer LLMs along the same computational path as the human brain

Joséphine Raugel, Jérémy Rapin, Stéphane d'Ascoli, Valentin Wyart, Jean-Remi King

Keywords: Large Language Models, LLMs, Emergence, Neuroscience, Brain, Alignment, Language, Magnetoencephalography

TL;DR: Emergence of an alignment between LLMs' and the brain's computational dynamics, and key factors allowing it : scaling and context size.

Abstract:

Recent studies suggest that the representations learned by large language models (LLMs) are partially aligned to those of the human brain.
However, whether this representational alignment arises from a similar sequence of computations remains elusive.

In this study, we explore this question by examining temporally-resolved brain signals of participants listening to 10 hours of an audiobook.
We study these neural dynamics jointly with a benchmark encompassing 17 LLMs varying in size and architecture type.

Our analyses reveal that LLMs and the brain generate representations in a similar order: specifically, activations in the initial layers of LLMs tend to best align with early brain responses, while the deeper layers of LLMs tend to best align with later brain responses.

This brain-LLM alignment is consistent across transformers and recurrent architectures.
However, its emergence depends on both model size and context length.

Overall, the alignment between LLMs and the brain provides novel elements supporting a partial convergence between biological and artificial neural networks.

Primary Area: Neuroscience and cognitive science (e.g., neural coding, brain-computer interfaces)

Submission Number: 20413