EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

How do ML practitioners perceive explainability? an interview study of practices and challenges

Umm-e- Habiba, Mohammad Kasra Habib, Justus Bogner, Jonas Fritzsch, Stefan Wagner

Empirical Software Engineering · 2025-01 · 30 (1)

DOI: 10.1007/s10664-024-10565-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Empirical Software Engineering, online erschienen am 01.11.2024. Verfasst von Umm-e- Habiba und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Education and Research, Universität Stuttgart.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable artificial intelligence (XAI) is a field of study that focuses on the development process of AI-based systems while making their decision-making processes understandable and transparent for users. Research already identified explainability as an emerging requirement for AI-based systems that use machine learning (ML) techniques. However, there is a notable absence of studies investigating how ML practitioners perceive the concept of explainability, the challenges they encounter, and the potential trade-offs with other quality attributes. In this study, we want to discover how practitioners define explainability for AI-based systems and what challenges they encounter in making them explainable. Furthermore, we explore how explainability interacts with other quality attributes. To this end, we conducted semi-structured interviews with 14 ML practitioners from 11 companies. Our study reveals diverse viewpoints on explainability and applied practices. Results suggest that the importance of explainability lies in enhancing transparency, refining models, and mitigating bias. Methods like SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanation (LIME) are frequently used by ML practitioners to understand how models work, while tailored approaches are typically adopted to meet the specific requirements of stakeholders. Moreover, we have discerned emerging challenges in eight categories. Issues such as effective communication with non-technical stakeholders and the absence of standardized approaches are frequently stated as recurring hurdles. We contextualize these findings in terms of requirements engineering and conclude that industry currently lacks a standardized framework to address arising explainability needs.

Förderung

  • German Federal Ministry of Education and Research
  • Universität Stuttgart

Zitieren

APA

Habiba, U., Habib, M. K., Bogner, J., Fritzsch, J., & Wagner, S. (2025). How do ML practitioners perceive explainability? an interview study of practices and challenges. Empirical Software Engineering, 30(1). https://doi.org/10.1007/s10664-024-10565-2

Vancouver

Habiba U, Habib MK, Bogner J, Fritzsch J, Wagner S. How do ML practitioners perceive explainability? an interview study of practices and challenges. Empirical Software Engineering. 2025;30(1). doi:10.1007/s10664-024-10565-2

BibTeX
@article{Habiba2025,
  author = {Habiba, Umm-e- and Habib, Mohammad Kasra and Bogner, Justus and Fritzsch, Jonas and Wagner, Stefan},
  title = {How do ML practitioners perceive explainability? an interview study of practices and challenges},
  journal = {Empirical Software Engineering},
  year = {2025},
  volume = {30},
  number = {1},
  doi = {10.1007/s10664-024-10565-2}
}
Kostenlos starten →