Learning interactions to boost human creativity with bandits and GPT-4
This addresses the problem of overcoming cognitive limits in creativity for humans, though it is incremental as it builds on existing bandit and AI methods.
The paper tackled the problem of boosting human creativity in semantic feature generation tasks by using algorithmically-generated hints selected via a multi-armed bandit, finding that both humans and GPT-4 benefited similarly from hints, with bandits preferring the same prompting strategy for both.
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.