# A Layered Multi-Expert Framework for Long-Context Mental Health Assessments

arXiv: https://arxiv.org/abs/2501.13951 · HTML: https://mlsanity.com/paper/2501.13951/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 20 Jan 2025.

## Builds on (most cited first, 4 of 4)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Illuminate: A novel approach for depression detection with explainable analysis and proactive therapy using prompt engineering](https://mlsanity.com/paper/2402.05127/) (2024)
- [Advancing Mental Health Pre-Screening: A New Custom GPT for Psychological Distress Assessment](https://mlsanity.com/paper/2408.01614/) (2024)

## Built on by (most cited first, 4 of 4)

- [EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety](https://mlsanity.com/paper/2504.09689/) (2025)
- [Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models](https://mlsanity.com/paper/2508.17674/) (2025)
- [Expert-Level Crisis Detection in Mental Health Conversations](https://mlsanity.com/paper/2606.10380/) (2026)
- [LLMersion: A Local-First AI Agent Framework for Low-Cost Home Language Learning toward Educational Equity](https://mlsanity.com/paper/2609.29672/) (2026)

## Abstract (arXiv)

Long-form mental health assessments pose unique challenges for large language models (LLMs), which often exhibit hallucinations or inconsistent reasoning when handling extended, domain-specific contexts. We introduce Stacked Multi-Model Reasoning (SMMR), a layered framework that leverages multiple LLMs and specialized smaller models as coequal 'experts'. Early layers isolate short, discrete subtasks, while later layers integrate and refine these partial outputs through more advanced long-context models. We evaluate SMMR on the DAIC-WOZ depression-screening dataset and 48 curated case studies with psychiatric diagnoses, demonstrating consistent improvements over single-model baselines in terms of accuracy, F1-score, and PHQ-8 error reduction. By harnessing diverse 'second opinions', SMMR mitigates hallucinations, captures subtle clinical nuances, and enhances reliability in high-stakes mental health assessments. Our findings underscore the value of multi-expert frameworks for more trustworthy AI-driven screening.