GRIM：面向游戏的基于图形的交互式叙事可视化系统

GRIM: GRaph-based Interactive narrative visualization for gaMes

November 15, 2023

作者: Jorge Leandro, Sudha Rao, Michael Xu, Weijia Xu, Nebosja Jojic, Chris Brockett, Bill Dolan

cs.AI

摘要

基于对话的角色扮演游戏（RPG）需要强大的叙事能力。这些叙事可能需要数年时间来撰写，通常涉及一个庞大的创作团队。在这项工作中，我们展示了大型生成文本模型在协助这一过程中的潜力。GRIM是一个原型系统，即基于图形的互动叙事可视化系统，用于游戏，它生成一个包含分支故事线的丰富叙事图，与设计师提供的高层叙事描述和约束相匹配。游戏设计师可以通过自动生成符合原始叙事和约束内的编辑的新子图来交互式地编辑该图。我们演示了GRIM与GPT-4结合使用，为四个知名故事生成具有不同上下文约束的分支叙事。

English

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. GRIM, a prototype GRaph-based Interactive narrative visualization system for gaMes, 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 GRIM in conjunction with GPT-4, generating branching narratives for four well-known stories with different contextual constraints.