Can ChatGPT Predict What I Think? Exploring Transformer Models' Prediction of Human Information Processes

Meghna BhadraMeghna Bhadra, Marco RagniMarco Ragni

Meghna Bhadra, Marco Ragni
Can ChatGPT Predict What I Think? Exploring Transformer Models' Prediction of Human Information Processes
Poster at the AAAI Bridge Programme on Collaborative AI and Modeling of Humans in the 39th Annual AAAI Conference, February 2025

Details
Bibtex

KurzfassungAbstract
While AI and machine learning often aim to solve problems optimally, cognitive modeling focuses on describing general patterns of human information processing. This paper investigates the application of transformer-based models for the automatic generation of cognitive models tailored to individual users. Using a dataset of 50 participants solving 64 syllogistic reasoning tasks, we demonstrate that transformer architectures can predict individual responses with accuracy comparable to the best cognitive models. Our methodology not only leverages the opaque processes of transformers but also aims to generate interpretable algorithms. Our approach achieves approximately 47% accuracy, placing it second to the best state-of-the-art cognitive model at 49%, while outperforming several established cognitive models.
Forschungsgruppe:Research Group: Computational LogicComputational Logic

@misc{BR2025,
  author = {Meghna Bhadra and Marco Ragni},
  title  = {Can {ChatGPT} Predict What I Think? Exploring Transformer Models'
            Prediction of Human Information Processes},
  year   = {2025},
  month  = {February}
}