When combinations of humans and AI are useful: A systematic review and meta-analysis
This work addresses the problem of understanding effective human-AI collaboration for researchers and practitioners, but it is incremental as it synthesizes existing studies rather than introducing new methods.
The paper conducted a meta-analysis of over 100 experimental studies to determine when human-AI combinations outperform either alone, finding that on average they perform worse, with losses in decision-making tasks and gains in content creation tasks.
Inspired by the increasing use of AI to augment humans, researchers have studied human-AI systems involving different tasks, systems, and populations. Despite such a large body of work, we lack a broad conceptual understanding of when combinations of humans and AI are better than either alone. Here, we addressed this question by conducting a meta-analysis of over 100 recent experimental studies reporting over 300 effect sizes. First, we found that, on average, human-AI combinations performed significantly worse than the best of humans or AI alone. Second, we found performance losses in tasks that involved making decisions and significantly greater gains in tasks that involved creating content. Finally, when humans outperformed AI alone, we found performance gains in the combination, but when the AI outperformed humans alone we found losses. These findings highlight the heterogeneity of the effects of human-AI collaboration and point to promising avenues for improving human-AI systems.