cs.LGNov 10, 2026

Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models

Authors: Boyoung Kwon, Jiyoon Seo, Sang Ho Lee

Organizations: Graduate School of Data Science, KAIST · School of Digital Humanities and Computational Social Sciences, KAIST · Department of Brain & Cognitive Sciences, KAIST

Abstract

Computational cognitive modeling has traditionally relied on manual model construction, which is a time-intensive process that requires substantial domain expertise. Although recent LLM-based approaches have begun to automate model generation, they often prioritize predictive accuracy at the expense of structural plausibility and parameter identifiability. We introduce DisCo, an LLM-guided framework that discovers interpretable symbolic cognitive models through evolutionary search with two structural components: a Validator that filters structurally invalid models, and a Cleaner that promotes parameter identifiability by removing redundant parameters. Across three behavioral tasks, DisCo consistently discovers models that achieve performance competitive with task-specific baselines. Ablation analyses show that the Validator is important for recovering psychologically meaningful structure. Without this component, models tend to violate behavioral constraints and show less consistent associations with external cognitive measures. These results suggest that LLM-driven model discovery, when coupled with appropriate structural constraints, can yield cognitively plausible models that go beyond predictive fit.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Think-Aloud Reshapes Automated Cognitive Model Discovery Beyond Behavior

    May 6, 2026Hanbo Xie, Akshay K. Jagadish, Lan Pan +1Risky Decision-MakingComputational Cognitive Modeling

  2. Hypothesis-guided discovery of cognitive algorithms via program refinement

    Oct 1, 2026Huiwen Alex Yang, Mark K. Ho, Bill D. ThompsonComputational Cognitive ModelingAutomated Algorithm Discovery

  3. Cognitive Foundations for Reasoning and Their Manifestation in LLMs

    Nov 20, 2025Shuyue Stella Li, Priyanka Kargupta, Haocheng Wang +9Structured Reasoning in Language ModelsLanguage Model Reasoning Evaluation