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.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Audit of ChatGPT, Copilot, Gemini and Perplexity finds ~16% of cited sources are AI-generated across 712 queries on politics, health and environment.
A multi-stage pipeline on Gaia DR3 data yields a census of 1,256 Stellar Snake candidates with 802,489 member stars, validated against external catalogs.
Embeddings reliably capture authorial stylistic features in French literary texts, and these signals persist after LLM rewriting while showing model-specific patterns.
HARDAT applies HDBSCAN clustering with differential-rotation tracking and SVM-based polarity inversion line extraction to magnetograms, claiming superior sensitivity, accuracy and identity continuity over DBSCAN-based DSARD and NOAA catalogs.
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.