用大模型生成可交互的多分支故事，让玩家改写主角人生轨迹。
WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models
- 通过元提示让大模型自动生成剧情分支，保持逻辑连贯。
- 基于原有主线构建分支图谱，支持动态叙事追踪。
- 适合游戏设计、创意写作与互动叙事研究者使用。
WHAT-IF 是一个基于零样本元提示的系统，能将预设线性剧情转化为可交互的分支叙事。玩家在游戏过程中选择由 GPT-4 生成的关键决策点，触发故事分支。系统通过分析故事核心情节，生成结构合理、语义连贯的替代剧情。所有分支以图结构存储，既用于后续提示生成，也保障了最终互动小说系统的叙事完整性。演示地址：https://what-if-game.github.io/。
原文摘要 · Abstract (English)
WHAT-IF -- Writing a Hero's Alternate Timeline through Interactive Fiction -- is a system that uses zero-shot meta-prompting to create branching narratives from a prewritten story. Played as an interactive fiction (IF) game, WHAT-IF lets the player choose between decisions that the large language model (LLM) GPT-4 generates as possible branches in the story. Starting with an existing linear plot as input, a branch is created at each key decision taken by the main character. By meta-prompting the LLM to consider the major plot points from the story, the system produces coherent and well-structured alternate storylines. WHAT-IF stores the branching plot tree in a graph which helps it to both keep track of the story for prompting and maintain the structure for the final IF system. A demo of WHAT-IF can be found at https://what-if-game.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。