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

Lakshmi Nair, Evana Gizzi, Jivko Sinapov
5/2/2024
cs.AIcs.LG

Official code: lnairGT/creative-problem-solving-LLMs (7 stars, last commit 2024-10-09).

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

View on arXivView PDF

Code Implementations(1)

A repo containing data and code for preliminary experiments demonstrating creative problem solving in LLMs, inspired by Computational Creativity literature.

72PythonJan 23, 20242 years ago

Similar Papers

Cite this paper

@article{nair2024creative,
  title  = {Creative Problem Solving in Large Language and Vision Models -- What Would it Take?},
  author = {Lakshmi Nair and Evana Gizzi and Jivko Sinapov},
  year   = {2024},
  eprint = {2405.01453},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.01453v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.01453.svg)](https://codeofpaper.com/paper/2405.01453)

Discussion