Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models

A framework that trains a small large language model to predict future reader responses as low-dimensional trajectories, then uses a larger off-the-shelf writer LLM to generate story segments following those trajectories, improves trajectory-based fidelity to human-written stories by 12%-35% while largely preserving story coherence, according to arXiv paper 2611.00469v1. The approach learns readerly dynamics from high-quality human-written stories rather than directly modeling high-dimensional story content.

arXiv:2611.00469v1 Announce Type: new Abstract: Large language models LLMs are increasingly used to generate stories, but these stories struggle to reproduce engaging readerly dynamics, the evolving reader responses that shape narrative experience. To address this challenge, we propose a framework that learns readerly dynamics from high-quality human-written stories and uses them to guide story generation. Instead of directly modeling high-dimensional story content, we train a small LLM to predict future reader responses as low-dimensional trajectories. We then leverage the strong instruction-following capability of a larger, off-the-shelf writer LLM to generate story segments that follow these predicted trajectories within a given story setting. Our framework improves trajectory-based fidelity to human-written stories by 12%-35% while largely preserving story coherence.