How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling

2026-09-02

AI Summary

本文分析了大语言模型通过构建故事环境来创造虚构世界的方法，使用五种叙事空间类型对比AI与人类创作的故事，发现两者在空间运用上存在显著差异。

Abstract

In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworld construction. We compare 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg. Building on prior work, we operationalize setting through five types of narrative space: "action", "perceived," "visual," "descriptive" and "no space", identified using fine-tuned BERT classifiers for German and English. We generate narratives using GPT 4.1, LlaMA 3.3, Mistral 3.2, and Gemma 3 and compare their spatial distributions to a human-authored baseline. We find that human-authored texts predominantly employ "action space," grounding narratives in embodied character-environment interaction, whereas LLMs systematically overproduce "perceived space," emphasizing atmosphere and affect. This divergence remains stable across narrative time. Overall, our findings show that LLMs exhibit worldbuilding patterns that differ consistently from human-authored fiction in ways that are both model-specific and language-sensitive.

Problem

• Large Language Models
• worldbuilding strategies
• setting
• narrative space
• AI-generated stories

Innovation

• worldbuilding strategies
• narrative space
• Large Language Models (LLMs)
• action space
• perceived space