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

arXiv: https://arxiv.org/abs/2609.02482 · HTML: https://mlsanity.com/paper/2609.02482/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?](https://mlsanity.com/paper/2407.01119/) (2024)
- [Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection](https://mlsanity.com/paper/2504.11900/) (2025)
- [Collective Critics for Creative Story Generation](https://mlsanity.com/paper/2410.02428/) (2024)
- [Where Do People Tell Stories Online? Story Detection Across Online Communities](https://mlsanity.com/paper/2311.09675/) (2023)
- [Can Language Models Represent the Past without Anachronism?](https://mlsanity.com/paper/2505.00030/) (2025)
- [AI with Emotions: Exploring Emotional Expressions in Large Language Models](https://mlsanity.com/paper/2504.14706/) (2025)
- [Grounding Characters and Places in Narrative Texts](https://mlsanity.com/paper/2305.17561/) (2023)
- [Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis](https://mlsanity.com/paper/2102.02111/) (2021)
- [The Zero Body Problem: Probing LLM Use of Sensory Language](https://mlsanity.com/paper/2504.06393/) (2025)
- [Language Models Don't Learn the Physical Manifestation of Language](https://mlsanity.com/paper/2402.11349/) (2024)

## Abstract (arXiv)

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.