This paper considers how interactions with AI algorithms can boost human creative thought. We employ a psychological task that demonstrates limits on human creativity, namely semantic feature generation: given a concept name, respondents must list as many of its features as possible. Human participants typically produce only a fraction of the features they know before getting stuck.'' In experiments with humans and with a large language model (GPT-4), we contrast behavior in the standard task versus a variant in which participants can ask for algorithmically-generated hints. Algorithm choice is administered by a multi-armed bandit whose reward indicates whether the hint helped generating more features. Humans and the AI show similar benefits from hints, and remarkably, bandits learning from AI responses prefer the same prompting strategy as those learning from human behavior. The results suggest that strategies for boosting human creativity via computer interactions can be learned by bandits run on groups of simulated participants.

Authors:

Ara Vartanian: University of Wisconsin Madison; Xiaoxi Sun: University of Wisconsin Madison; Yun-Shiuan Chuang: University of Wisconsin Madison; Siddharth Suresh: University of Wisconsin-Madison; Jerry Zhu: University of Wisconsin-Madison; Timothy Rogers: UW-Madison