Metraipolis › archive › dc_4fa1957f5ef4

The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation — arXiv:2609.14677

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14677
License (as archived)
CC0-1.0
Archived
2026-10-15T23:15:23.389Z
SHA-256 of the archived text
67e1dd52ec5ba0e5f13c4a6b74b4588a76ceec33f7629ac14ea92073eda7910d
Stable URL of this page
https://metraipolis.com/documento/dc_4fa1957f5ef4

How to cite

The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation — arXiv:2609.14677 — arXiv (en), https://arxiv.org/abs/2609.14677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fa1957f5ef4 (Metraipolis archive dc_4fa1957f5ef4, sha256 67e1dd52ec5ba0e5f13c4a6b74b4588a76ceec33f7629ac14ea92073eda7910d)
BibTeX
@misc{dc4fa1957f5ef4,
  title = {The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation — arXiv:2609.14677},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14677},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fa1957f5ef4; sha256 67e1dd52ec5ba0e5f13c4a6b74b4588a76ceec33f7629ac14ea92073eda7910d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have changed the way people engage with stories. Drawing on public chatbot logs, we can see that when users generate stories, they iteratively edit their prompts to explore narrative possibilities, adjusting characters, redirecting plots, and swapping fictional universes. As aggregated data, these prompts represent rich traces of creative preference at scale. Yet story generation evaluation benchmarks rely on static, one-shot prompts that cannot capture this exploratory behavior. In this work, we study how users revise consecutive story prompts in the wild. Using a dataset of naturally occurring user-chatbot conversations, we construct WildStories, a sample of 275,635 story generation prompts (labeled with story format, prompt components, and explicitness), and WildEdits, a collection of 24,291 edit trees that model how users iteratively edit base story prompts and explore branching story possibilities. From these trees we develop a framework of edit types crossing four directions (adding, removing, changing, and extending) with fourteen targets (e.g., plot, character, genre). We then use our datasets and this framework to analyze user behavior in navigating narrative space via LLMs. Finally, we show how automated permutations based on the framework can be used for story generation benchmarking. Content Warning: This paper works with "wild" chatbot logs, which often include toxic and sexually explicit themes.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.14677 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:51:09.900Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).