Cognitive Modeling of Semantic Fluency Using Transformers

TL;DR

This paper explores using transformer-based language models to predict human performance in semantic fluency tasks, aiming to understand their potential as models of human cognition and memory retrieval strategies.

Contribution

It introduces hyperparameter hypothesization for cognitive profiling and demonstrates that TLMs can outperform existing models in predicting individual differences in semantic fluency.

Findings

TLMs can predict individual differences in semantic fluency better than existing models.

Preliminary evidence suggests TLMs may offer insights into human memory retrieval strategies.

The approach opens new avenues for cognitive modeling using deep language models.

Abstract

Can deep language models be explanatory models of human cognition? If so, what are their limits? In order to explore this question, we propose an approach called hyperparameter hypothesization that uses predictive hyperparameter tuning in order to find individuating descriptors of cognitive-behavioral profiles. We take the first step in this approach by predicting human performance in the semantic fluency task (SFT), a well-studied task in cognitive science that has never before been modeled using transformer-based language models (TLMs). In our task setup, we compare several approaches to predicting which word an individual performing SFT will utter next. We report preliminary evidence suggesting that, despite obvious implementational differences in how people and TLMs learn and use language, TLMs can be used to identify individual differences in human fluency task behaviors better than existing computational models, and may offer insights into human memory retrieval strategies -- cognitive process not typically considered to be the kinds of things TLMs can model. Finally, we discuss the implications of this work for cognitive modeling of knowledge representations.