EUVIMEDEUVIMED entdecken
Crossref

Explanations Can Reduce Overreliance on AI Systems During Decision-Making

Helena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, Tobias Gerstenberg, Michael S. Bernstein, Ranjay Krishna

Proceedings of the ACM on Human-Computer Interaction · 14.04.2023 · 7 (CSCW1) · 1-38

DOI: 10.1145/3579605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 16.04.2023. Verfasst von Helena Vasconcelos und 5 weiteren Autor:innen. Die Arbeit wurde bisher 409-mal zitiert (Crossref) und nennt 97 Literaturangaben. Gefördert von: Snap Inc..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI produces explanations for its predictions, compared to only providing predictions. Some have argued that overreliance results from cognitive biases or uncalibrated trust, attributing overreliance to an inevitability of human cognition. By contrast, our paper argues that people strategically choose whether or not to engage with an AI explanation, demonstrating empirically that there are scenarios where AI explanations reduce overreliance. To achieve this, we formalize this strategic choice in a cost-benefit framework, where the costs and benefits of engaging with the task are weighed against the costs and benefits of relying on the AI. We manipulate the costs and benefits in a maze task, where participants collaborate with a simulated AI to find the exit of a maze. Through 5 studies (N = 731), we find that costs such as task difficulty (Study 1), explanation difficulty (Study 2, 3), and benefits such as monetary compensation (Study 4) affect overreliance. Finally, Study 5 adapts the Cognitive Effort Discounting paradigm to quantify the utility of different explanations, providing further support for our framework. Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.

Förderung

  • Snap Inc.

Zitieren

APA

Vasconcelos, H., Jörke, M., Grunde-McLaughlin, M., Gerstenberg, T., Bernstein, M. S., & Krishna, R. (2023). Explanations Can Reduce Overreliance on AI Systems During Decision-Making. Proceedings of the ACM on Human-Computer Interaction, 7(CSCW1), 1-38. https://doi.org/10.1145/3579605

Vancouver

Vasconcelos H, Jörke M, Grunde-McLaughlin M, Gerstenberg T, Bernstein MS, Krishna R. Explanations Can Reduce Overreliance on AI Systems During Decision-Making. Proceedings of the ACM on Human-Computer Interaction. 2023;7(CSCW1):1-38. doi:10.1145/3579605

BibTeX
@article{Vasconcelos2023,
  author = {Vasconcelos, Helena and Jörke, Matthew and Grunde-McLaughlin, Madeleine and Gerstenberg, Tobias and Bernstein, Michael S. and Krishna, Ranjay},
  title = {Explanations Can Reduce Overreliance on AI Systems During Decision-Making},
  journal = {Proceedings of the ACM on Human-Computer Interaction},
  year = {2023},
  volume = {7},
  number = {CSCW1},
  pages = {1--38},
  doi = {10.1145/3579605}
}
Kostenlos starten →