Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation
Seraphina Goldfarb-Tarrant, Haining Feng, Nanyun Peng
TL;DR
Open-domain storytelling remains challenging for AI; this work builds and evaluates an interactive system enabling planning, editing, revision, and novelty control to study where human collaboration most helps. Two interaction modes—cross-model and intra-model—provide varying degrees of human steering across planning and writing, with Plan-and-Revise discriminators guiding creative and relevant outputs. Across six experimental variants, human-in-the-loop setups consistently improve story quality and user engagement, and targeted interventions can improve specific weaknesses like creativity or coherence. The results suggest practical benefits for human-in-the-loop storytelling and point to future data-driven discriminators trained on collaborative feedback.
Abstract
Story composition is a challenging problem for machines and even for humans. We present a neural narrative generation system that interacts with humans to generate stories. Our system has different levels of human interaction, which enables us to understand at what stage of story-writing human collaboration is most productive, both to improving story quality and human engagement in the writing process. We compare different varieties of interaction in story-writing, story-planning, and diversity controls under time constraints, and show that increased types of human collaboration at both planning and writing stages results in a 10-50% improvement in story quality as compared to less interactive baselines. We also show an accompanying increase in user engagement and satisfaction with stories as compared to our own less interactive systems and to previous turn-taking approaches to interaction. Finally, we find that humans tasked with collaboratively improving a particular characteristic of a story are in fact able to do so, which has implications for future uses of human-in-the-loop systems.