Artificial intelligence (AI) can improve human decision-making in various
application areas. Ideally, collaboration between humans and AI should lead to
complementary team performance (CTP) -- a level of performance that neither of
them can attain individually. So far, however, CTP has rarely been observed,
suggesting an insufficient understanding of the complementary constituents in
human-AI collaboration that can contribute to CTP in decision-making. This work
establishes a holistic theoretical foundation for understanding and developing
human-AI complementarity. We conceptualize complementarity by introducing and
formalizing the notion of complementarity potential and its realization.
Moreover, we identify and outline sources that explain CTP. We illustrate our
conceptualization by applying it in two empirical studies exploring two
different sources of complementarity potential. In the first study, we focus on
information asymmetry as a source and, in a real estate appraisal use case,
demonstrate that humans can leverage unique contextual information to achieve
CTP. In the second study, we focus on capability asymmetry as an alternative
source, demonstrating how heterogeneous capabilities can help achieve CTP. Our
work provides researchers with a theoretical foundation of complementarity in
human-AI decision-making and demonstrates that leveraging sources of
complementarity potential constitutes a viable pathway toward effective
human-AI collaboration.

人工智能在各个应用领域可以提高人类决策能力。理想情况下，人类与人工智能之间的合作应该能达到互补的团队表现，尽管迄今为止，很少观察到这种互补的现象，这表明对于决策中人工智能与人类合作中的互补成分的理解仍然不足。本文建立了一个关于理解和开发人工智能与人类互补性的整体理论基础。我们通过引入和形式化互补潜力及其实现的概念来概括互补性。此外，我们确定并概述了解释互补团队表现的来源。我们通过两项实证研究将我们的概念应用于实证验证两个不同的互补潜力源。第一项研究中，我们关注信息不对称作为一种来源，并在房地产评估应用案例中证明人类能够利用独特的背景信息实现互补团队表现。在第二项研究中，我们关注能力不对称作为另一种来源，展示了异质能力如何帮助实现互补团队表现。我们的工作为研究人员提供了关于人工智能决策中互补性的理论基础，并证明利用互补潜力来源是有效人工智能与人类合作的途径。