Structural Similarities Between Language Models and Neural Response Measurements

Jiaang Li, Antonia Karamolegkou, Yova Kementchedjhieva, Mostafa Abdou, Sune Lehmann, Anders Søgaard

Submission Track: Proceedings

Keywords: fMRI, large language models, neural networks, representation, understanding

TL;DR: The larger neural language models get, the more their representations are structurally similar to neural response measurements from brain imaging.

Abstract: Large language models have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy) recordings of activations during listening or reading, from which we can extract similar representations of words and phrases. Here we study the extent to which the geometries induced by these representations, share similarities in the context of brain decoding. We find that the larger neural language models get, the more their representations are structurally similar to neural response measurements from brain imaging.

Submission Number: 15