This site is under active development. Some content may be AI-assisted or incomplete. If something looks off, it probably is.
Do Language Models Agree with Human Perceptions of Suspense in Stories?
NLP
Computational Linguistics
Narrative
An investigation into whether language models can distinguish and estimate suspense in text sequences compared to human judgments.
Publication Details
arXiv: 2508.15794
Abstract
This work investigates whether language models can distinguish whether a text is intended to induce suspense in people, whether LMs can accurately estimate the relative amount of suspense within a text sequence as compared to human judgments, and whether LMs can properly capture the human perception for the rise and fall of suspense across multiple text segments.