EUVIMEDEUVIMED entdecken
Crossref

Selective Explanations: Leveraging Human Input to Align Explainable AI

Vivian Lai, Yiming Zhang, Chacha Chen, Q. Vera Liao, Chenhao Tan

Proceedings of the ACM on Human-Computer Interaction · 28.09.2023 · 7 (CSCW2) · 1-35

DOI: 10.1145/3610206 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 04.10.2023. Verfasst von Vivian Lai und 4 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While a vast collection of explainable AI (XAI) algorithms has been developed in recent years, they have been criticized for significant gaps with how humans produce and consume explanations. As a result, current XAI techniques are often found to be hard to use and lack effectiveness. In this work, we attempt to close these gaps by making AI explanations selective ---a fundamental property of human explanations---by selectively presenting a subset of model reasoning based on what aligns with the recipient's preferences. We propose a general framework for generating selective explanations by leveraging human input on a small dataset. This framework opens up a rich design space that accounts for different selectivity goals, types of input, and more. As a showcase, we use a decision-support task to explore selective explanations based on what the decision-maker would consider relevant to the decision task. We conducted two experimental studies to examine three paradigms based on our proposed framework: in Study 1, we ask the participants to provide critique-based or open-ended input to generate selective explanations (self-input). In Study 2, we show the participants selective explanations based on input from a panel of similar users (annotator input). Our experiments demonstrate the promise of selective explanations in reducing over-reliance on AI and improving collaborative decision making and subjective perceptions of the AI system, but also paint a nuanced picture that attributes some of these positive effects to the opportunity to provide one's own input to augment AI explanations. Overall, our work proposes a novel XAI framework inspired by human communication behaviors and demonstrates its potential to encourage future work to make AI explanations more human-compatible.

Förderung

  • National Science Foundation

Zitieren

APA

Lai, V., Zhang, Y., Chen, C., Liao, Q. V., & Tan, C. (2023). Selective Explanations: Leveraging Human Input to Align Explainable AI. Proceedings of the ACM on Human-Computer Interaction, 7(CSCW2), 1-35. https://doi.org/10.1145/3610206

Vancouver

Lai V, Zhang Y, Chen C, Liao QV, Tan C. Selective Explanations: Leveraging Human Input to Align Explainable AI. Proceedings of the ACM on Human-Computer Interaction. 2023;7(CSCW2):1-35. doi:10.1145/3610206

BibTeX
@article{Lai2023,
  author = {Lai, Vivian and Zhang, Yiming and Chen, Chacha and Liao, Q. Vera and Tan, Chenhao},
  title = {Selective Explanations: Leveraging Human Input to Align Explainable AI},
  journal = {Proceedings of the ACM on Human-Computer Interaction},
  year = {2023},
  volume = {7},
  number = {CSCW2},
  pages = {1--35},
  doi = {10.1145/3610206}
}
Kostenlos starten →