Summary of Collective Critics For Creative Story Generation, by Minwook Bae et al.
Collective Critics for Creative Story Generation
by Minwook Bae, Hyounghun Kim
First submitted to arxiv on: 3 Oct 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 proposed Collective Critics for Creative Story Generation framework (CritiCS) addresses the challenge of generating long stories with narrative coherence using Large Language Models (LLMs). The framework integrates a collective revision mechanism to promote creativity and expressiveness in long-form story generation. It consists of a plan refining stage (CrPlan) and a story generation stage (CrText), where a group of LLM critics and one leader collaborate to refine drafts throughout multiple rounds. This approach enables interactive human-machine collaboration in story writing and significantly enhances story creativity and reader engagement while maintaining narrative coherence. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CritiCS is a new way to make stories with computers. Right now, machines are good at making short texts like tweets or Facebook posts. But they’re not as good at making longer stories that people want to read. The problem is that these stories often don’t have much creativity or emotion in them. To fix this, the researchers created a special kind of computer program that can work with humans to make better stories. This program uses other computers to help it come up with ideas and make sure the story makes sense. They tested their program and found that it made stories that people liked more than stories made by just one machine. |
