Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models
cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 55 pages, 20 figures, 18 tables, including references and the appendix
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models (LLMs) are increasingly used to generate stories, but these stories struggle to reproduce engaging readerly dynamics…
Terminology
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.
Sources
- StoryScope: Investigating idiosyncrasies in AI fiction
- Do Language Models Agree with Human Perceptions of Suspense in Stories?
- Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning
- Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning
- Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
- Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence Embeddings
- Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data