Tag
The study compares longitudinal, cross-sectional, and graph-based models for predicting adolescent substance use onset using ABCD Study data, showing that combined approaches achieve better accuracy with AUC-ROC values above 0.79.
DMT-CBT proposes a framework for longitudinal therapeutic state modeling in CBT counseling, addressing the need for multi-session, multimodal inference and intervention. It introduces DMTCorpus, a synthetic multi-session dataset, and shows improvements in counseling fidelity and therapeutic alliance over existing methods.
LiFT is a longitudinal instruction fine-tuning framework that unifies diverse temporal NLP tasks under a shared instruction schema with curriculum-based training. Evaluated across OLMo, LLaMA, and Qwen models, LiFT consistently outperforms base-model in-context learning, especially on out-of-distribution data and rare change events.