EUVIMEDEUVIMED entdecken
Crossref

Viewpoint: The Future of Human-Centric Explainable Artificial Intelligence (XAI) is not Post-Hoc Explanations

Vinitra Swamy, Jibril Frej, Tanja Käser

Journal of Artificial Intelligence Research · 02.09.2025 · 84

DOI: 10.1613/jair.1.17970 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 02.09.2025. Verfasst von Vinitra Swamy und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems. As models get larger, more ubiquitous, and pervasive in aspects of daily life, explainability is necessary to minimize adverse effects of model mistakes. Unfortunately, current approaches in human-centric XAI (e.g. predictive tasks in healthcare, education, or personalized ads) tend to rely on a single post-hoc explainer, whereas recent work has identified systematic disagreement between post-hoc explainers when applied to the same instances of underlying black-box models. In this viewpoint paper, we therefore present a call for action to address the limitations of current state-of-the-art explainers. We propose a shift from post-hoc explainability to designing interpretable neural network architectures. We identify five needs of human-centric XAI (real-time, accurate, actionable, human-interpretable, and consistent) and propose two possible routes forward for interpretable-by-design neural network workflows (adaptive routing and temporal diagnostics). We postulate that the future of human-centric XAI is neither in explaining black-boxes nor in reverting to traditional, interpretable models, but in neural networks that are intrinsically interpretable.

Zitieren

APA

Swamy, V., Frej, J., & Käser, T. (2025). Viewpoint: The Future of Human-Centric Explainable Artificial Intelligence (XAI) is not Post-Hoc Explanations. Journal of Artificial Intelligence Research, 84. https://doi.org/10.1613/jair.1.17970

Vancouver

Swamy V, Frej J, Käser T. Viewpoint: The Future of Human-Centric Explainable Artificial Intelligence (XAI) is not Post-Hoc Explanations. Journal of Artificial Intelligence Research. 2025;84. doi:10.1613/jair.1.17970

BibTeX
@article{Swamy2025,
  author = {Swamy, Vinitra and Frej, Jibril and Käser, Tanja},
  title = {Viewpoint: The Future of Human-Centric Explainable Artificial Intelligence (XAI) is not Post-Hoc Explanations},
  journal = {Journal of Artificial Intelligence Research},
  year = {2025},
  volume = {84},
  doi = {10.1613/jair.1.17970}
}
Kostenlos starten →