SARD: A Human-AI Collaborative Story Generation
This addresses the challenge for storytellers using AI tools, but it is incremental as it identifies limitations to guide future development.
The authors tackled the problem of human-AI collaborative story generation by proposing SARD, a drag-and-drop visual interface using large language models, and found that it caused mental overhead and distraction for writers while AI-generated stories were less lexically diverse.
Generative artificial intelligence (GenAI) has ushered in a new era for storytellers, providing a powerful tool to ignite creativity and explore uncharted narrative territories. As technology continues to advance, the synergy between human creativity and AI-generated content holds the potential to redefine the landscape of storytelling. In this work, we propose SARD, a drag-and-drop visual interface for generating a multi-chapter story using large language models. Our evaluation of the usability of SARD and its creativity support shows that while node-based visualization of the narrative may help writers build a mental model, it exerts unnecessary mental overhead to the writer and becomes a source of distraction as the story becomes more elaborated. We also found that AI generates stories that are less lexically diverse, irrespective of the complexity of the story. We identified some patterns and limitations of our tool that can guide the development of future human-AI co-writing tools.