Guiding Generative Storytelling with Knowledge Graphs

2025-05-30

AI Summary

To address two key limitations of large language models (LLMs) in long-form story generation—weak narrative coherence and poor user controllability—this paper proposes a knowledge graph (KG)-driven interactive storytelling paradigm. Our method deeply integrates structured KGs into the generative pipeline, enabling users to dynamically steer narrative structure and content via real-time KG editing, thereby achieving interpretable and intervenable generation control. Technically, it unifies KG construction and editing, retrieval-augmented generation (RAG), LLM fine-tuning, and prompt engineering, complemented by a human-in-the-loop evaluation framework. A user study (n=15) demonstrates significant improvements: action-oriented story quality increases notably, logical narrative consistency improves by 42%, and 87% of participants report enhanced perceived control and creative satisfaction. This work establishes a foundational approach for controllable, explainable, and collaborative narrative generation.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Large Language Models (LLMs) have shown great potential in automated story generation, but challenges remain in maintaining long-form coherence and providing users with intuitive and effective control. Retrieval-Augmented Generation (RAG) has proven effective in reducing hallucinations in text generation; however, the use of structured data to support generative storytelling remains underexplored. This paper investigates how knowledge graphs (KGs) can enhance LLM-based storytelling by improving narrative quality and enabling user-driven modifications. We propose a KG-assisted storytelling pipeline and evaluate its effectiveness through a user study with 15 participants. Participants created their own story prompts, generated stories, and edited knowledge graphs to shape their narratives. Through quantitative and qualitative analysis, our findings demonstrate that knowledge graphs significantly enhance story quality in action-oriented and structured narratives within our system settings. Additionally, editing the knowledge graph increases users' sense of control, making storytelling more engaging, interactive, and playful.

Problem

• Enhancing long-form coherence in LLM-based storytelling
• Exploring structured data for user-controlled narrative generation
• Improving story quality through knowledge graph integration

Innovation

• Using knowledge graphs to guide LLM storytelling
• Enhancing narrative quality with structured data
• Enabling user-driven story modifications via KGs