Appropriate Reliance and Imperfect explainable AI
Speaker: Prof. Niklas Kühl
Abstract: In this insightful presentation, we will delve into the frontiers of explainability within artificial intelligence and its pivotal role in enhancing collaborative human-AI interactions. As AI systems become integral to our decision-making processes, it's imperative to scrutinize not only their recommendations but also the accompanying explanations. Therefore, we first conceptualize the phenomena of “appropriate reliance”. Our rigorous mixed-methods research, involving 136 participants, critically examines the repercussions of inaccuracies in AI-generated explanations during a complex bird species identification task. We will dissect how these imperfections interact with the decision-makers' expertise. The insights gained illuminate the nuanced ways in which flawed explainable AI (XAI) can skew reliance and team performance.
Short Bio: Niklas Kühl is Full Professor of Information Systems and Human-Centric Artificial Intelligence at the University of Bayreuth. He holds a senior management position at the Fraunhofer Institute for Applied Information Technology (FIT) and is Director at the FIM Research Institute for Information Management as well as Senior Expert Artificial Intelligence at IBM. Prior to his role in Bayreuth, he worked at IBM as a Managing Consultant in the area of Data Science and completed his PhD and habilitation at the Karlsruhe Institute of Technology. In his research, teaching and practical work, Niklas Kühl focuses on the interface of technical topics from artificial intelligence and machine learning with relevant problems from industry and society.