The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories
This work addresses methodological issues for researchers in cognitive and developmental science, but it is incremental as it builds on existing critiques without introducing new empirical results.
The paper examines the challenges of using pre-trained language models (PLMs) as theories in cognitive science, particularly in developmental alignment, and proposes criteria to address pitfalls in mapping model performance to human cognition.
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.