The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories

TL;DR

This paper critically examines the use of pre-trained language models as models of human cognition and development, highlighting challenges, lessons learned, and criteria for their credible application in cognitive science.

Contribution

It provides a comprehensive review of the assumptions, challenges, and lessons learned in using PLMs as cognitive and developmental models, proposing criteria for their credible use.

Findings

Identifies key challenges in using PLMs as cognitive models.

Highlights pitfalls and limitations of current approaches.

Proposes criteria for credible application of PLMs in cognitive science.

Abstract

Many studies have evaluated the cognitive alignment of Pre-trained Language Models (PLMs), i.e., their correspondence to adult performance across a range of cognitive domains. Recently, the focus has expanded to the developmental alignment of these models: identifying phases during training where improvements in model performance track improvements in children's thinking over development. However, there are many challenges to the use of PLMs as cognitive science theories, including different architectures, different training data modalities and scales, and limited model interpretability. In this paper, we distill lessons learned from treating PLMs, not as engineering artifacts but as cognitive science and developmental science models. We review assumptions used by researchers to map measures of PLM performance to measures of human performance. We identify potential pitfalls of this approach to understanding human thinking, and we end by enumerating criteria for using PLMs as credible accounts of cognition and cognitive development.