# Exploring Large-Scale Language Models to Evaluate EEG-Based Multimodal Data for Mental Health

arXiv: https://arxiv.org/abs/2408.07313 · HTML: https://mlsanity.com/paper/2408.07313/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2024.

## Built on by (most cited first, 13 of 13)

- [CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model](https://mlsanity.com/paper/2506.09110/) (2025)
- [NeuroChat: A Neuroadaptive AI Chatbot for Customizing Learning Experiences](https://mlsanity.com/paper/2503.07599/) (2025)
- [Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?](https://mlsanity.com/paper/2505.18215/) (2025)
- [AER-LLM: Ambiguity-aware Emotion Recognition Leveraging Large Language Models](https://mlsanity.com/paper/2409.18339/) (2024)
- [Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification](https://mlsanity.com/paper/2410.18686/) (2024)
- [Efficient and Personalized Mobile Health Event Prediction via Small Language Models](https://mlsanity.com/paper/2409.18987/) (2024)
- [Large Language Models for EEG: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2506.06353/) (2025)
- [Foundation Models for Cross-Domain EEG Analysis Application: A Survey](https://mlsanity.com/paper/2508.15716/) (2025)
- [HealthSLM-Bench: Benchmarking Small Language Models for Mobile and Wearable Healthcare Monitoring](https://mlsanity.com/paper/2509.07260/) (2025)
- [NeuroSkill(tm): Proactive Real-Time Agentic System Capable of Modeling Human State of Mind](https://mlsanity.com/paper/2603.03212/) (2026)
- [CTG-Insight: A Multi-Agent Interpretable LLM Framework for Cardiotocography Analysis and Classification](https://mlsanity.com/paper/2507.22205/) (2025)
- [RAICL: Retrieval-Augmented In-Context Learning for Vision-Language-Model Based EEG Seizure Detection](https://mlsanity.com/paper/2601.17844/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)

## Abstract (arXiv)

Integrating physiological signals such as electroencephalogram (EEG), with other data such as interview audio, may offer valuable multimodal insights into psychological states or neurological disorders. Recent advancements with Large Language Models (LLMs) position them as prospective ``health agents'' for mental health assessment. However, current research predominantly focus on single data modalities, presenting an opportunity to advance understanding through multimodal data. Our study aims to advance this approach by investigating multimodal data using LLMs for mental health assessment, specifically through zero-shot and few-shot prompting. Three datasets are adopted for depression and emotion classifications incorporating EEG, facial expressions, and audio (text). The results indicate that multimodal information confers substantial advantages over single modality approaches in mental health assessment. Notably, integrating EEG alongside commonly used LLM modalities such as audio and images demonstrates promising potential. Moreover, our findings reveal that 1-shot learning offers greater benefits compared to zero-shot learning methods.