LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment
This research addresses the challenge of zero-shot predictions on unseen subjects in EEG-based Brain-Computer Interfaces, which is incremental as it builds on existing cross-subject analysis methods.
The study tackled the problem of cross-subject variability in EEG signal decoding by using Large Language Models (LLMs) as denoising agents to extract subject-independent semantic features, resulting in enhanced generalizability for Brain-Computer Interfaces.
Decoding human activity from EEG signals has long been a popular research topic. While recent studies have increasingly shifted focus from single-subject to cross-subject analysis, few have explored the model's ability to perform zero-shot predictions on EEG signals from previously unseen subjects. This research aims to investigate whether deep learning methods can capture subject-independent semantic information inherent in human EEG signals. Such insights are crucial for Brain-Computer Interfaces (BCI) because, on one hand, they demonstrate the model's robustness against subject-specific temporal biases, and on the other, they significantly enhance the generalizability of downstream tasks. We employ Large Language Models (LLMs) as denoising agents to extract subject-independent semantic features from noisy EEG signals. Experimental results, including ablation studies, highlight the pivotal role of LLMs in decoding subject-independent semantic information from noisy EEG data. We hope our findings will contribute to advancing BCI research and assist both academia and industry in applying EEG signals to a broader range of applications.