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

arXiv: https://arxiv.org/abs/2412.10582 · HTML: https://mlsanity.com/paper/2412.10582/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 55 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 14 of 14)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds](https://mlsanity.com/paper/2010.00685/) (2020)
- [Bringing Stories Alive: Generating Interactive Fiction Worlds](https://mlsanity.com/paper/2001.10161/) (2020)
- [TellMeWhy: A Dataset for Answering Why-Questions in Narratives](https://mlsanity.com/paper/2106.06132/) (2021)
- [LARP: Language-Agent Role Play for Open-World Games](https://mlsanity.com/paper/2312.17653/) (2023)
- [GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence](https://mlsanity.com/paper/2310.05388/) (2023)
- [SWAG: Storytelling With Action Guidance](https://mlsanity.com/paper/2402.03483/) (2024)
- [CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding](https://mlsanity.com/paper/2212.10754/) (2022)
- [End-to-end Story Plot Generator](https://mlsanity.com/paper/2310.08796/) (2023)

## Built on by (most cited first, 1 of 1)

- [SENSE: State-aware Emotion Navigation Storytelling Engine](https://mlsanity.com/paper/2610.07666/) (2026)

## Abstract (arXiv)

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/.