WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models

TL;DR

WHAT-IF is a system that leverages zero-shot meta-prompting with GPT-4 to generate coherent branching narratives from a linear story, enabling interactive fiction with multiple storylines based on user choices.

Contribution

It introduces a novel zero-shot meta-prompting approach for creating branching narratives from linear stories using large language models.

Findings

Generates coherent alternative storylines at decision points.

Maintains a structured story graph for interactive fiction.

Demonstrates effective use of meta-prompting with GPT-4.

Abstract

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/.