Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity
This work addresses the need for reliable and useful AI tools to enhance human creativity in cross-domain analogical reasoning, though it is incremental as it builds on prior proofs-of-concept.
The paper tackled the problem of systematically evaluating Large Language Models' (LLMs) capacity to augment cross-domain analogical reasoning for human creative work, finding that LLM-generated analogies were frequently helpful (median 4 out of 5 rating) and led to observable changes in problem formulations in about 80% of cases, with up to 25% of outputs rated as potentially harmful.
Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of 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 cross-domain 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 bring 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.