Summary of A Survey on Large Language Model Hallucination Via a Creativity Perspective, by Xuhui Jiang et al.
A Survey on Large Language Model Hallucination via a Creativity Perspective
by Xuhui Jiang, Yuxing Tian, Fengrui Hua, Chengjin Xu, Yuanzhuo Wang, Jian Guo
First submitted to arxiv on: 2 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Human-Computer Interaction (cs.HC)
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 abstract explores the potential creative benefits of hallucinations in large language models (LLMs), suggesting that they may contribute to LLM applications by fostering creativity. The survey begins with a review of the taxonomy of hallucinations and their negative impact on LLM reliability in critical applications, before exploring historical examples and recent theories on the topic. It delves into definitions and assessment methods of creativity, and systematically reviews literature on transforming and harnessing hallucinations for creativity in LLMs. The paper concludes by discussing future research directions, emphasizing the need to further explore and refine the application of hallucinations in creative processes within LLMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large language models (LLMs) are smart computers that can understand and generate human-like text. Sometimes, these models make mistakes called “hallucinations.” Instead of seeing these mistakes as bad things, this survey looks at how they might actually help the models be more creative. The survey starts by explaining what hallucinations are and why they’re a problem in some cases. Then it looks at examples from history and recent ideas that show how hallucinations could help the models think outside the box. |
