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 language AI (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.

翻译：本文探讨如何通过与AI算法的交互来激发人类的创造性思维。我们采用了一项能够揭示人类创造力局限性的心理学任务——语义特征生成任务：给定一个概念名称，受试者需尽可能多地列举其属性特征。人类受试者通常只能列举出他们已知特征的一小部分，随后便陷入"思维卡顿"状态。通过人类受试者与语言AI（GPT-4）的对比实验，我们考察了标准任务与改良任务中的行为差异——在改良任务中，参与者可请求算法生成的提示。算法选择由多臂老虎机管理，其奖励机制反映提示是否有助于生成更多特征。研究发现，人类与AI从提示中获得的收益具有相似性；值得注意的是，基于AI响应进行学习的老虎机，与基于人类行为进行学习的老虎机，倾向于采用相同的提示策略。研究结果表明，通过计算机交互提升人类创造力的策略，可通过在模拟参与者群体上运行的老虎机算法习得。