# Think-Aloud Reshapes Automated Cognitive Model Discovery Beyond Behavior

arXiv: https://arxiv.org/abs/2605.05091 · HTML: https://mlsanity.com/paper/2605.05091/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 2 of 2)

- [Generating Computational Cognitive Models using Large Language Models](https://mlsanity.com/paper/2502.00879/) (2025)
- [Scaling up the think-aloud method](https://mlsanity.com/paper/2505.23931/) (2025)

## Built on by (most cited first, 1 of 1)

- [Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist](https://mlsanity.com/paper/2606.26448/) (2026)

## Abstract (arXiv)

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.