Brain-inspired cognitive state modeling of complex English discourse reading: an LLM-parameterized hierarchical semi-Markov approach
Bing Xie, Yongjin Hu, Linlin Zhao · 2026
Read Brain-inspired cognitive state modeling of complex English discourse reading: an LLM-parameterized hierarchical semi-Markov approach by Bing Xie, Yongjin Hu, Linlin Zhao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13632470.txt.
Description
Bing Xie, Yongjin Hu, and Linlin Zhao model the mental states of a reader moving through hard English texts, in a 2026 paper. Reading weaves word access, sentence parsing, and cross sentence inference over time. Their model stacks three levels, word, sentence, and discourse, inside a hidden semi Markov frame whose settings come from a large language model's embeddings.
On 1,200 passages, the model scored a macro F1 of 0.86 and located state boundaries with 0.83 accuracy. Its duration estimates missed by about half a unit on average. The authors offer the system as an interpretable account of how comprehension adapts while reading.
Catalog record
| CREATOR | Bing Xie, Yongjin Hu, Linlin Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |