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

Lakshmi Nair, Evana Gizzi, Jivko Sinapov


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.
Anthology ID:
2024.findings-emnlp.700
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11978–11994
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.700
DOI:
Bibkey:
Cite (ACL):
Lakshmi Nair, Evana Gizzi, and Jivko Sinapov. 2024. Creative Problem Solving in Large Language and Vision Models - What Would it Take?. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11978–11994, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Creative Problem Solving in Large Language and Vision Models - What Would it Take? (Nair et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.700.pdf
Software:
 2024.findings-emnlp.700.software.zip