Incorporating think-aloud traces with behavioral data in LLM-driven model discovery for risky choice yields higher held-out predictive accuracy and shifts most participants' best models from explicit-comparator to integrated-utility structures.
NeurIPS 2023 AI for science workshop , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Think-Aloud Reshapes Automated Cognitive Model Discovery Beyond Behavior
Incorporating think-aloud traces with behavioral data in LLM-driven model discovery for risky choice yields higher held-out predictive accuracy and shifts most participants' best models from explicit-comparator to integrated-utility structures.