Summary of Creative Problem Solving in Large Language and Vision Models — What Would It Take?, by Lakshmi Nair et al.
Creative Problem Solving in Large Language and Vision Models – What Would it Take?
by Lakshmi Nair, Evana Gizzi, Jivko Sinapov
First submitted to arxiv on: 2 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
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 We explore the integration of Computational Creativity (CC) with large language and vision models (LLVMs) to enhance creative problem-solving capabilities. This paper presents preliminary experiments demonstrating the effectiveness of applying CC principles to address this limitation. By integrating CC with LLVMs, we aim to foster discussions on creative problem solving in these models at prestigious machine learning venues. Our approach leverages CC techniques, such as analogy-making and constraint satisfaction, to improve the creative problem-solving abilities of LLVMs. The code for our experiments is publicly available at https://github.com/lnairGT/creative-problem-solving-LLMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine if computers could come up with creative solutions to problems. This paper talks about how we can make that happen by combining two areas of research: large language and vision models, and Computational Creativity. We show some early results that suggest this combination can be effective in solving complex problems. The goal is to start a conversation about how these models can be used for creative problem-solving at top conferences. |
Keywords
» Artificial intelligence » Machine learning
