P2P - from Posts to Patterns: An LLM Ensemble Approach to Mental Health Dynamics Detection

Le résumé fourni par la source

The automatic detection of mental health dy- namics represents a challenging and socially relevant task, requiring models to capture sub- tle psychological changes over time. Large language models have demonstrated remark- able capabilities in clinical and diagnostic con- texts, yet their outputs often lack consistency and may diverge significantly across different model families and prompting strategies. This paper presents the USAI team’s submission to the CLPsych 2026 Shared Task, targeting Tasks 1.1, 1.2, 2, and 3.1. We propose an ensemble-based approach combining multiple open-source large language models, where the contribution of each model is weighted accord- ing to its alignment with clinically grounded human annotations on the training set. Our system achieves competitive results across the evaluated subtasks, with particularly strong per- formance on Tasks 1.2 and 2.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.