Exploring the relationship between features calculated from contextual embeddings and EEG band power during sentence reading in Chinese

YAO WANGTiantian XueXingyu Yang^*

• Beijing Language and Culture University, Beijing, China

Contextual embeddings-a core component of large language models (LLMs) that generate dynamic vector representations capturing words' semantic properties-have demonstrated structural similarities to brain activity patterns at the single-word level. This alignment supports the theoretical framework proposing vector-based neural coding for natural language processing in the brain, where linguistic units may be represented as context-sensitive vectors analogous to LLM-derived embeddings. Building on this framework, we hypothesize that cumulative distance metrics between contextual embeddings of adjacent linguistic units (words/Chinese characters) in sentence contexts may quantitatively reflect neural activation intensity during reading comprehension. Using largescale EEG datasets collected during reading tasks, we systematically investigated the relationship between these computationally derived distance features and frequency-specific band power measures associated with neural activity. While observed effects may be somehow text-or datasetdependent, our analyses revealed associations between various distance metrics and neural responses, consistent with predictions derived from the vector-based neural coding framework.