LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment

TL;DR

This paper demonstrates that Large Language Models can effectively extract subject-independent semantic information from noisy EEG signals, improving cross-subject brain signal analysis for Brain-Computer Interfaces.

Contribution

It introduces the novel use of LLMs as denoising agents to enhance zero-shot, cross-subject EEG decoding, advancing BCI robustness and generalizability.

Findings

LLMs improve decoding of semantic info from EEG

Enhanced cross-subject EEG prediction accuracy

LLMs demonstrate robustness against subject-specific biases

Abstract

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.