Sind die Entscheidungen einer KI eigentlich wirklich transparent und wie lässt sich die Erklärbarkeit der Entscheidungen transparenter gestalten, sodass auch Menschen diese verstehen?
Genau damit beschäftigt sich die neue Publikation „Explanation as a social practice: Toward a conceptual framework for the social design of AI systems” von Katharina Rohlfing, Philipp Cimiano, Ingrid Scharlau, Tobias Matzner, Heike Buhl, Hendrik Buschmeier, Elena Esposito, Angela Grimminger, Barbara Hammer, Reinhold Häb-Umbach, Ilona Horwath, Eyke Hüllermeier, Friederike Kern, Stefan Kopp, Kirsten Thommes, Axel-Cyrille Ngonga Ngomo, Carsten Schulte, Henning Wachsmuth, Petra Wagner und Britta Wrede.
Abstract:
The recent surge of interest in explainability in artificial intelligence (XAI) is propelled by not only technological advancements in machine learning, but also by regulatory initiatives to foster transparency in algorithmic decision making. In this article, we revise the current concept of explainability and identify three limitations: passive explainee, narrow view on the social process, and undifferentiated assessment of understanding. In order to overcome these limitations, we present explanation as a social practice in which explainer and explainee co-construct understanding on the microlevel. We view the co-construction on a microlevel as embedded into a macrolevel, yielding expectations concerning, e.g., social roles or partner models: Typically, the role of the explainer is to provide an explanation and to adapt it to the current level of understanding of the explainee; the explainee, in turn, is expected to provide cues that guide the explainer. Building on explanations being a social practice, we present a conceptual framework that aims to guide future research in XAI. The framework relies on the key concepts of monitoring and scaffolding to capture the development of interaction. We relate our conceptual framework and our new perspective on explaining to transparency and autonomy as objectives considered for XAI.
Zum neuen Paper geht's hier.