Guiding Generative Storytelling with Knowledge Graphs

TL;DR

This paper explores how knowledge graphs can enhance large language model storytelling by improving narrative coherence and user control, demonstrated through a two-stage user study with positive engagement and specific narrative improvements.

Contribution

It introduces a KG-assisted storytelling pipeline that integrates editable knowledge graphs with LLMs, focusing on long-form narrative quality and user-driven modifications.

Findings

Improved action-oriented, structurally explicit narratives

Participants felt a strong sense of control and engagement

No significant improvement for introspective stories

Abstract

Large language models (LLMs) have shown great potential in story generation, but challenges remain in maintaining long-form coherence and effective, user-friendly control. Retrieval-augmented generation (RAG) has proven effective in reducing hallucinations in text generation; while knowledge-graph (KG)-driven storytelling has been explored in prior work, this work focuses on KG-assisted long-form generation and an editable KG coupled with LLM generation in a two-stage user study. This work investigates how KGs can enhance LLM-based storytelling by improving narrative quality and enabling user-driven modifications. We propose a KG-assisted storytelling pipeline and evaluate it in a user study with 15 participants. Participants created prompts, generated stories, and edited KGs to shape their narratives. Quantitative and qualitative analysis finds improvements concentrated in action-oriented, structurally explicit narratives under our settings, but not for introspective stories. Participants reported a strong sense of control when editing the KG, describing the experience as engaging, interactive, and playful.