Creative Problem Solving in Large Language and Vision Models -- What Would it Take?

TL;DR

This paper explores integrating Computational Creativity principles with large language and vision models to enhance their ability for creative problem solving, presenting preliminary experiments and advocating for further research in this area.

Contribution

It introduces the application of CC principles to LLVMs for creative problem solving and encourages discussion and research in this interdisciplinary area.

Findings

Preliminary experiments demonstrate potential of CC in LLVMs

Highlights need for further research in creative problem solving

Code availability promotes reproducibility and collaboration

Abstract

We advocate for a strong integration of Computational Creativity (CC) with research in large language and vision models (LLVMs) to address a key limitation of these models, i.e., creative problem solving. We present preliminary experiments showing how CC principles can be applied to address this limitation. Our goal is to foster discussions on creative problem solving in LLVMs and CC at prestigious ML venues. Our code is available at: https://github.com/lnairGT/creative-problem-solving-LLMs