WhatELSE: Shaping Narrative Spaces at Configurable Level of Abstraction for AI-bridged Interactive Storytelling

2025-02-25

AI Summary

In generative AI–driven interactive narrative, authors struggle to control the open-ended narrative space emergent from AI behavior. This paper introduces NarrativeSpace, a novel framework that pioneers a tripartite visualization paradigm—narrative pivots, outlines, and variants—coupled with language-level abstraction control to automatically construct, hierarchically abstract, and interactively visualize the narrative possibility space. Our method integrates large language model–guided narrative planning, hierarchical abstraction modeling, real-time event generation, and interactive visualization. A user study (N=12) and technical evaluation demonstrate that authors can efficiently perceive, edit, and execute narrative spaces, enabling high-engagement, coherence-preserving real-time interactive narratives. The core contribution is the first systematic transformation of an inherently uncontrollable generative narrative space into a perceptible, configurable, and executable structured design artifact.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Generative AI significantly enhances player agency in interactive narratives (IN) by enabling just-in-time content generation that adapts to player actions. While delegating generation to AI makes IN more interactive, it becomes challenging for authors to control the space of possible narratives - within which the final story experienced by the player emerges from their interaction with AI. In this paper, we present WhatELSE, an AI-bridged IN authoring system that creates narrative possibility spaces from example stories. WhatELSE provides three views (narrative pivot, outline, and variants) to help authors understand the narrative space and corresponding tools leveraging linguistic abstraction to control the boundaries of the narrative space. Taking innovative LLM-based narrative planning approaches, WhatELSE further unfolds the narrative space into executable game events. Through a user study (N=12) and technical evaluations, we found that WhatELSE enables authors to perceive and edit the narrative space and generates engaging interactive narratives at play-time.

Problem

• AI-bridged interactive storytelling
• control narrative possibility spaces
• generate executable game events

Innovation

• AI-bridged interactive storytelling system
• LLM-based narrative planning approaches
• Configurable narrative space control tools