Dialogue-based Role Playing Games (RPGs) require powerful storytelling. The narratives of these may take years to write and typically involve a large creative team. In this work, we demonstrate the potential of large generative text models to assist this process. \textbf{GRIM}, a prototype \textbf{GR}aph-based \textbf{I}nteractive narrative visualization system for ga\textbf{M}es, generates a rich narrative graph with branching storylines that match a high-level narrative description and constraints provided by the designer. Game designers can interactively edit the graph by automatically generating new sub-graphs that fit the edits within the original narrative and constraints. We illustrate the use of \textbf{GRIM} in conjunction with GPT-4, generating branching narratives for four well-known stories with different contextual constraints.

翻译：对话式角色扮演游戏（RPG）需要强大的叙事能力，其剧情往往需要耗费数年时间创作，通常涉及庞大的创作团队。本研究展示了大型生成式文本模型辅助这一过程的潜力。我们提出的原型系统\textbf{GRIM}（基于图谱的游戏交互式叙事可视化系统）能够生成包含分支故事线的丰富叙事图谱，使其匹配设计师提供的高级叙事描述与约束条件。游戏设计师可通过自动生成与原始叙事和约束条件相匹配的新子图谱，对现有图谱进行交互式编辑。我们展示了\textbf{GRIM}与GPT-4的协同应用案例，为四个具有不同语境约束的知名故事生成了分支叙事。