EUVIMEDEUVIMED entdecken
Crossref

Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration

Hasan Amin, Ming Yin, Rajiv Khanna

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (21) · 17337-17346

DOI: 10.1609/aaai.v40i21.38786 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hasan Amin und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can inadvertently erode human trust and cause them to ignore AI advice precisely when it is most needed. Conversely, an aligned AI fosters trust yet risks reinforcing suboptimal human behavior and lowering human-AI team performance. In this paper, we start by identifying this fundamental tension between performance-boosting (i.e., complementarity) and trust-building (i.e., alignment) as an inherent limitation of the traditional approach for training a single AI model to assist human decision making. To overcome this, we introduce a novel, human-centered adaptive AI ensemble that strategically toggles between two specialist AI models—the aligned model and the complementary model—based on contextual cues, using an elegantly simple yet provably near-optimal Rational Routing Shortcut mechanism. Comprehensive theoretical analyses elucidate why the adaptive AI ensemble is effective and when it yields maximum benefits. Moreover, experiments on both simulated and real-world data show that when humans are assisted by the adaptive AI ensemble in decision making, they can achieve significantly higher performance than when they are assisted by single AI models that are trained to either optimize for its independent performance or even the human-AI team performance.

Zitieren

APA

Amin, H., Yin, M., & Khanna, R. (2026). Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence, 40(21), 17337-17346. https://doi.org/10.1609/aaai.v40i21.38786

Vancouver

Amin H, Yin M, Khanna R. Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(21):17337-17346. doi:10.1609/aaai.v40i21.38786

BibTeX
@article{Amin2026,
  author = {Amin, Hasan and Yin, Ming and Khanna, Rajiv},
  title = {Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {21},
  pages = {17337--17346},
  doi = {10.1609/aaai.v40i21.38786}
}
Kostenlos starten →