Structural Similarities Between Language Models and Neural Response Measurements

Abstract

Large language models (LLMs) 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 activation 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. Code is available at \url{https://github.com/coastalcph/brainlm}.

arXiv commentNeurReps@NeurIPS 2023

References in corpus (9)

• Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• The Debate Over Understanding in AI's Large Language Models
• A Simple Method for Commonsense Reasoning
• Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)
• The Vector Grounding Problem
• Brain2Word: Decoding Brain Activity for Language Generation
• Do Vision and Language Models Share Concepts? A Vector Space Alignment Study