Large Language Models for EEG: A Comprehensive Survey and Taxonomy

2025-06-02

AI Summary

This study addresses the fundamental challenges at the intersection of large language models (LLMs) and electroencephalography (EEG). We propose the first systematic taxonomy—spanning representation learning, EEG-to-language decoding, cross-modal generation, and clinical applications—to structure this emerging domain. Methodologically, we introduce a novel LLM-based paradigm specifically designed for EEG: it unifies modeling principles and evaluation protocols, bridges theoretical gaps between natural language processing and neural signal analysis, and leverages Transformer architectures enhanced with fine-tuning, few-shot, and zero-shot learning strategies tailored to EEG’s temporal dynamics and multimodal alignment requirements. Our contribution includes a comprehensive review of over 120 state-of-the-art works, a reproducible methodology framework, and an open-source resource guide. This work establishes a foundational toolkit for neural decoding, brain–computer interfaces, and clinical decision support systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The growing convergence between Large Language Models (LLMs) and electroencephalography (EEG) research is enabling new directions in neural decoding, brain-computer interfaces (BCIs), and affective computing. This survey offers a systematic review and structured taxonomy of recent advancements that utilize LLMs for EEG-based analysis and applications. We organize the literature into four domains: (1) LLM-inspired foundation models for EEG representation learning, (2) EEG-to-language decoding, (3) cross-modal generation including image and 3D object synthesis, and (4) clinical applications and dataset management tools. The survey highlights how transformer-based architectures adapted through fine-tuning, few-shot, and zero-shot learning have enabled EEG-based models to perform complex tasks such as natural language generation, semantic interpretation, and diagnostic assistance. By offering a structured overview of modeling strategies, system designs, and application areas, this work serves as a foundational resource for future work to bridge natural language processing and neural signal analysis through language models.

Problem

• LLMs for EEG-based neural decoding and BCIs
• Survey of LLM applications in EEG analysis
• Bridging NLP and neural signal analysis

Innovation

• LLM-inspired foundation models for EEG
• EEG-to-language decoding techniques
• Cross-modal generation with EEG