Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement

TL;DR

This paper introduces DOME, a novel method for long-form story generation that enhances coherence and plot development through dynamic outlining, memory modules, and automatic consistency evaluation.

Contribution

The paper presents DOME, combining dynamic hierarchical outlining, memory-enhancement, and conflict analysis to improve long-form story generation quality.

Findings

DOME outperforms state-of-the-art methods in coherence and fluency.

Memory-Enhancement Module reduces contextual conflicts.

Temporal Conflict Analyzer effectively evaluates story consistency.

Abstract

Long-form story generation task aims to produce coherent and sufficiently lengthy text, essential for applications such as novel writingand interactive storytelling. However, existing methods, including LLMs, rely on rigid outlines or lack macro-level planning, making it difficult to achieve both contextual consistency and coherent plot development in long-form story generation. To address this issues, we propose Dynamic Hierarchical Outlining with Memory-Enhancement long-form story generation method, named DOME, to generate the long-form story with coherent content and plot. Specifically, the Dynamic Hierarchical Outline(DHO) mechanism incorporates the novel writing theory into outline planning and fuses the plan and writing stages together, improving the coherence of the plot by ensuring the plot completeness and adapting to the uncertainty during story generation. A Memory-Enhancement Module (MEM) based on temporal knowledge graphs is introduced to store and access the generated content, reducing contextual conflicts and improving story coherence. Finally, we propose a Temporal Conflict Analyzer leveraging temporal knowledge graphs to automatically evaluate the contextual consistency of long-form story. Experiments demonstrate that DOME significantly improves the fluency, coherence, and overall quality of generated long stories compared to state-of-the-art methods.