Think-Aloud Reshapes Automated Cognitive Model Discovery Beyond Behavior

TL;DR

This paper demonstrates that incorporating think-aloud process data into automated cognitive model discovery significantly improves predictive accuracy and alters model structures, revealing mechanisms not identifiable from behavioral data alone.

Contribution

It introduces the use of think-aloud traces as additional constraints in model discovery, leading to more accurate and structurally different cognitive models.

Findings

Models with think-aloud data outperform behavior-only models on predictive tasks.

Discovered models shift from Explicit comparator to Integrated utility in 69.4% of cases.

Process-level language data reshapes model structures beyond behavioral information.

Abstract

Computational cognitive models discovered using large language models have so far relied solely on behavioral data. However, it is well-known that models produced from the behavioral trajectory alone are typically under-determined. In this work, we explore the use of Think Aloud traces as an additional form of data constraint during automated model discovery. When applied to the domain of risky decision-making, we find that the models discovered with think-aloud achieve significantly improved predictive performance on held-out data. Additionally, we find that the discovered models belong to different structural classes than those discovered from behavior alone for the majority of participants (69.4\%), specifically, it shifts from Explicit comparator towards Integrated utility. These results suggest that process-level language data not only improve model fit, but also systematically reshape the structure of the discovered cognitive models, enabling the identification of mechanisms that are not recoverable from behavior alone.