STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation

2025-06-03

AI Summary

Existing automatic story generation methods suffer from insufficient narrative coherence and logical consistency. To address this, we propose a structured情节 node modeling approach grounded in Subject-Verb-Object (SVO) triplets, introducing a dual-module interactive architecture comprising a STORYLINE planning module and a dynamically updated Named Entity Knowledge Graph (NEKG). This work is the first to explicitly incorporate linguistic SVO structures into story planning and to enable real-time bidirectional semantic alignment between generation and the knowledge graph. Our method encompasses SVO triplet extraction, a dynamic narrative graph neural network, a modular plot planner, and a human-preference-driven multidimensional evaluation framework. Experiments demonstrate consistent superiority over baselines across coherence, creativity, engagement, and relevance; human preference evaluations yield an average win rate of 84.33%.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Stories are central to human culture, serving to share ideas, preserve traditions, and foster connections. Automatic story generation, a key advancement in artificial intelligence (AI), offers new possibilities for creating personalized content, exploring creative ideas, and enhancing interactive experiences. However, existing methods struggle to maintain narrative coherence and logical consistency. This disconnect compromises the overall storytelling experience, underscoring the need for substantial improvements. Inspired by human cognitive processes, we introduce Storyteller, a novel approach that systemically improves the coherence and consistency of automatically generated stories. Storyteller introduces a plot node structure based on linguistically grounded subject verb object (SVO) triplets, which capture essential story events and ensure a consistent logical flow. Unlike previous methods, Storyteller integrates two dynamic modules, the STORYLINE and narrative entity knowledge graph (NEKG),that continuously interact with the story generation process. This integration produces structurally sound, cohesive and immersive narratives. Extensive experiments demonstrate that Storyteller significantly outperforms existing approaches, achieving an 84.33% average win rate through human preference evaluation. At the same time, it is also far ahead in other aspects including creativity, coherence, engagement, and relevance.

Problem

• Enhancing coherence in automatic story generation
• Ensuring logical consistency in AI-generated narratives
• Improving structural cohesion for immersive storytelling

Innovation

• Uses SVO triplets for plot node structure
• Integrates STORYLINE and NEKG dynamic modules
• Ensures coherent and consistent story generation