Brain-inspired cognitive state modeling of complex English discourse reading: an LLM-parameterized hierarchical semi-Markov approach
TL;DR
A brain-inspired, large-language-model-parameterized hierarchical hidden semi-Markov model that encodes lexical-, sentence- and discourse-level representations and maps contextual embeddings to state-emission, transition, and duration parameters is developed.
Abstract
Introduction Complex English discourse reading requires readers to integrate lexical access, syntactic parsing, local meaning construction, cross-sentence inference, and discourse monitoring over time. Methods We developed a brain-inspired, large-language-model-parameterized hierarchical hidden semi-Markov model that encodes lexical-, sentence-, and discourse-level representations and maps contextual embeddings to state-emission, transition, and duration parameters. Discourse-structure and cognitive-load constraints were incorporated into global decoding. Results Experiments on 1,200 English reading passages achieved a macro-F1 of 0.860, a boundary accuracy of 0.83, a duration MAE of 0.52, and a discourse-consistency correlation of 0.76. Discussion The results suggest that duration-aware latent-state modeling can provide an interpretable computational account of adaptive discourse comprehension while preserving explicit temporal structure.