CUNY team uses LLMs for mental health change analysis

Researchers from CUNY have developed a pipeline approach for analyzing mental health changes using social media data for the CLPsych 2026 Shared Task. Their system combines in-context learning from multiple open-weight large language models for classifying self-states and predicting timeline changes. The pipeline also includes a summarization component that leverages upstream predictions to describe mood dynamics over time, achieving top rankings in several task categories. AI

IMPACT Demonstrates a novel pipeline for analyzing mental health trends using LLMs, potentially improving early detection and intervention strategies.

RANK_REASON Academic paper detailing a novel approach to analyzing mental health changes using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• CLPsych 2026
• large language models

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →