# The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation

arXiv: https://arxiv.org/abs/2609.14677 · HTML: https://mlsanity.com/paper/2609.14677/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation](https://mlsanity.com/paper/2310.12953/) (2023)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild](https://mlsanity.com/paper/2407.11438/) (2024)
- [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://mlsanity.com/paper/2505.16023/) (2025)
- [Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection](https://mlsanity.com/paper/2504.11900/) (2025)
- [Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks](https://mlsanity.com/paper/2212.01350/) (2022)
- [Community Identity and User Engagement in a Multi-Community Landscape](https://mlsanity.com/paper/1705.09665/) (2017)
- [Where Do People Tell Stories Online? Story Detection Across Online Communities](https://mlsanity.com/paper/2311.09675/) (2023)
- [ShareChat: A Dataset of Chatbot Conversations in the Wild](https://mlsanity.com/paper/2512.17843/) (2025)
- [Exploring Prompt Engineering Practices in the Enterprise](https://mlsanity.com/paper/2403.08950/) (2024)
- [Sketch and Customize: A Counterfactual Story Generator](https://mlsanity.com/paper/2104.00929/) (2021)
- [Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney](https://mlsanity.com/paper/2311.12131/) (2023)
- [From Chat Logs to Collective Insights: Aggregative Question Answering](https://mlsanity.com/paper/2505.23765/) (2025)
- [Generative AI floods and dilutes the market for books](https://mlsanity.com/paper/2607.20349/) (2026)
- [Process-Oriented Evaluation of AI-Assisted Scientific Writing](https://mlsanity.com/paper/2606.15583/) (2026)

## Abstract (arXiv)

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.