SWAG: Storytelling With Action Guidance
This addresses the challenge of creating engaging automated stories for applications like entertainment or education, representing a novel method rather than an incremental improvement.
The paper tackled the problem of generating engaging long-form stories by introducing SWAG, a two-model feedback loop that frames story writing as a search problem, resulting in substantial outperformance over previous techniques as evaluated by GPT-4 and humans, with the pipeline using small open-source models surpassing GPT-3.5-Turbo.
Automated long-form story generation typically employs long-context large language models (LLMs) for one-shot creation, which can produce cohesive but not necessarily engaging content. We introduce Storytelling With Action Guidance (SWAG), a novel approach to storytelling with LLMs. Our approach frames story writing as a search problem through a two-model feedback loop: one LLM generates story content, and another auxiliary LLM is used to choose the next best "action" to steer the story's future direction. Our results show that SWAG can substantially outperform previous end-to-end story generation techniques when evaluated by GPT-4 and through human evaluation. Our SWAG pipeline using only small open-source models surpasses GPT-3.5-Turbo.