Recent advancements in Large Language Models have inspired the development of foundation models across various domains. In this study, we evaluate the efficacy of Large EEG Models (LEMs) by fine-tuning LaBraM, a state-of-the-art foundation EEG model, on a real-world stress classification dataset collected in a graduate classroom. Unlike previous studies that primarily evaluate LEMs using data from controlled clinical settings, our work assesses their applicability to real-world environments. We train a binary classifier that distinguishes between normal and elevated stress states using resting-state EEG data recorded from 18 graduate students during a class session. The best-performing fine-tuned model achieves a balanced accuracy of 90.47% with a 5-second window, significantly outperforming traditional stress classifiers in both accuracy and inference efficiency. We further evaluate the robustness of the fine-tuned LEM under random data shuffling and reduced channel counts. These results demonstrate the capability of LEMs to effectively process real-world EEG data and highlight their potential to revolutionize brain-computer interface applications by shifting the focus from model-centric to data-centric design.
View on arXiv@article{wang2025_2505.23042,
title={ From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data },
author={ Siwen Wang and Shitou Zhang and Wan-Lin Chen and Dung Truong and Tzyy-Ping Jung },
journal={arXiv preprint arXiv:2505.23042},
year={ 2025 }
}