Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System

TL;DR

This paper explores design techniques for using Large Language Models in interactive storytelling, exemplified by the Dramamancer system that converts story schemas into player-driven narratives.

Contribution

It introduces novel design techniques for integrating LLMs into interactive storytelling and discusses evaluation considerations for such systems.

Findings

Dramamancer effectively transforms story schemas into interactive narratives.

Design techniques improve author-player collaboration in storytelling.

Evaluation considerations guide future development of LLM-based narrative systems.

Abstract

The rise of Large Language Models (LLMs) has enabled a new paradigm for bridging authorial intent and player agency in interactive narrative. We consider this paradigm through the example of Dramamancer, a system that uses an LLM to transform author-created story schemas into player-driven playthroughs. This extended abstract outlines some design techniques and evaluation considerations associated with this system.