DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
Quick Answer
DreamerNLplus is a hybrid framework for modeling mental health dynamics from social media, achieving 2nd place in sequence-level summarization and 1st in improvement detection.
Quick Take
DreamerNLplus is a hybrid framework for modeling mental health dynamics from social media, achieving 2nd place in sequence-level summarization and 1st in improvement detection. It combines LLM-based data augmentation, DeBERTa classification, and Random Forest regression, while addressing challenges in temporal transitions and evaluation metrics.
Key Points
- Utilizes LLM-based data augmentation and DeBERTa for psychological state modeling.
- Employs few-shot prompting with Llama 3.1 for event detection.
- Achieved 1st place in improvement detection and 3rd in deterioration.
- Highlights challenges in classification-regression performance mismatch.
- Code and prompts available at GitHub for further research.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2605. 23052v1 Announce Type: new Abstract: We present DreamerNLplus, a hybrid framework for modeling mental health dynamics from social media timelines in the CLPsych 2026 shared task. Our system addresses three tasks: psychological state modeling, temporal change detection, and sequence-level summarization. For Task 1, we combine LLM-based data augmentation, DeBERTa classification, and Random Forest regression for structured state prediction.
For Task 2, we use few-shot prompting with a locally deployed Llama 3. 1 model to detect Switch and Escalation events using short-term temporal context. For Task 3. 1, we explore both a deterministic rule-based summarization pipeline and a few-shot LLM-based approach, ranking \textbf{2nd} officially. Our -based method achieves strong performance in Task 3.
2, ranking \textbf{1st} for Improvement and \textbf{3rd} for Deterioration, demonstrating its ability to capture recurrent psychological change patterns across timelines. Our analysis reveals key challenges, including the mismatch between classification and regression performance, the difficulty of modeling temporal transitions, and the disagreement between semantic and similarity-based evaluation metrics.
These findings highlight the complexity of modeling mental health dynamics and motivate future work on unified evaluation frameworks. We share our code and prompts at https://github. com/4dpicture/CLPsych2026
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.