Fine-Tuning Large Language Models Using EEG Microstate Features for Mental Workload Assessment

2025-08-10

AI Summary

Low accuracy in automatic recognition of cognitive load states (rest vs. load) remains a key challenge. Method: This study introduces, for the first time, the integration of EEG microstate features into a large language model (LLM) fine-tuning framework. Microstate segmentation, source-space back-projection reconstruction, and multidimensional feature extraction yield interpretable neurodynamic representations; task-oriented prompt engineering is then employed to construct a supervised fine-tuning dataset for end-to-end LLM optimization. Contribution/Results: The work establishes a novel paradigm—“neural-signal-enhanced generative AI”—transcending limitations of conventional discriminative models. Experiments demonstrate a significant +8.3% improvement in binary cognitive state classification accuracy using the microstate-augmented LLM, validating that EEG-derived features effectively enhance the LLM’s semantic-physiological alignment capability. This advances interpretable neural human–computer interaction.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Cognitive Modeling & Cognitive Systems: Simulating Human BehaviorNatural Language Processing: (Large) Language Models

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This study explores the intersection of electroencephalography (EEG) microstates and Large Language Models (LLMs) to enhance the assessment of cognitive load states. By utilizing EEG microstate features, the research aims to fine-tune LLMs for improved predictions of distinct cognitive states, specifically 'Rest' and 'Load'. The experimental design is delineated in four comprehensive stages: dataset collection and preprocessing, microstate segmentation and EEG backfitting, feature extraction paired with prompt engineering, and meticulous LLM model selection and refinement. Employing a supervised learning paradigm, the LLM is trained to identify cognitive load states based on EEG microstate features integrated into prompts, producing accurate discrimination of cognitive load. A curated dataset, linking EEG features to specified cognitive load conditions, underpins the experimental framework. The results indicate a significant improvement in model performance following the proposed fine-tuning, showcasing the potential of EEG-informed LLMs in cognitive neuroscience and cognitive AI applications. This approach not only contributes to the understanding of brain dynamics but also paves the way for advancements in machine learning techniques applicable to cognitive load and cognitive AI research.

Problem

• Enhancing cognitive load assessment using EEG and LLMs
• Fine-tuning LLMs with EEG microstate features for cognitive states
• Improving model performance for EEG-based cognitive load prediction

Innovation

• Fine-tuning LLMs with EEG microstate features
• Supervised learning for cognitive load discrimination
• EEG-informed prompts enhance model performance