Summary of Swag: Storytelling with Action Guidance, by Zeeshan Patel et al.
SWAG: Storytelling With Action Guidance
by Zeeshan Patel, Karim El-Refai, Jonathan Pei, Tianle Li
First submitted to arxiv on: 5 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces Storytelling With Action Guidance (SWAG), a novel approach to automated long-form story generation using large language models (LLMs). Unlike previous methods, which rely solely on LLMs for one-shot creation, SWAG frames storytelling as a search problem. This is achieved through a two-model feedback loop, where one LLM generates story content and another auxiliary LLM chooses the next best “action” to steer the story’s future direction. The results show that SWAG outperforms previous end-to-end story generation techniques when evaluated by GPT-4 and human evaluation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SWAG is a new way for computers to generate stories. It uses two types of language models to create a story that people will like. One model writes the story, and another model decides what should happen next. This makes the story more interesting and engaging than previous methods. The results show that SWAG works better than other ways of generating stories. |
Keywords
* Artificial intelligence * Gpt * One shot
