Fluid Transformers and Creative Analogies: Exploring Large Language Models’ Capacity for Augmenting Cross-Domain Analogical Creativity

Loading...
Thumbnail Image

Files

Ding et al.pdf (3.53 MB)
No. of downloads: 12

Publication or External Link

Date

2023-06-19

Advisor

Citation

Zijian Ding, Arvind Srinivasan, Stephen MacNeil, and Joel Chan. 2023. Fluid Transformers and Creative Analogies: Exploring Large Language Models’ Capacity for Augmenting Cross-Domain Analogical Creativity. In Creativity and Cognition (C&C ’23), June 19–21, 2023, Virtual Event, USA. ACM, New York, NY, USA, 17 pages.

Abstract

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofsof-concept of Large language Models’ (LLMs) ability to generate cross-domain analogies. However, the reliability and potential usefulness of this capacity for augmenting human creative work has received little systematic exploration. In this paper, we systematically explore LLMs capacity to augment cross-domain analogical reasoning. Across three studies, we found: 1) LLM-generated crossdomain analogies were frequently judged as helpful in the context of a problem reformulation task (median 4 out of 5 helpfulness rating), and frequently (∼80% of cases) led to observable changes in problem formulations, and 2) there was an upper bound of ∼25% of outputs being rated as potentially harmful, with a majority due to potentially upsetting content, rather than biased or toxic content. These results demonstrate the potential utility — and risks — of LLMs for augmenting cross-domain analogical creativity.

Notes

Rights