KIT | KIT-Bibliothek | Impressum | Datenschutz

Personalized Explanations

Becker, Maximilian ORCID iD icon 1
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

Machine learning systems are often hard to investigate and intransparent in their decision making . Explainable Artificial Intelligence (XAI) tries to make these systems more transparent. However, most work in the field focuses on technical aspects like maximizing metrics. The human aspects of explainability are often neglected. In this work, we present personalized explanations, which instead focus on the user. Personalized explanations can be adapted to individual users to be as useful and relevant as possible. They can be interacted with to give users the ability to engage in an explanatory dialog with the system. Finally, they should also protect user data to increase the trust in the explanation system.

Verlagsausgabe §
DOI: 10.5445/IR/1000161548
Veröffentlicht am 18.08.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2023
Sprache Englisch
Identifikator ISBN: 978-3-7315-1304-9
ISSN: 1863-6489
KITopen-ID: 1000161548
HGF-Programm 46.23.04 (POF IV, LK 01) Engineering Security for Production Systems
Erschienen in Proceedings of the 2022 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. Ed.: J. Beyerer
Verlag KIT Scientific Publishing
Seiten 1-10
Serie Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ; 62
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page