Projekt

Zur Projekt-Website

Decisions that directly affect individual lives or society as a whole are increasingly aided by intelligent systems. Domains of application include, but are not limited to, traffic control, the health sector, human resource management, or the police and judiciary systems. Intelligent systems play a vital role in shaping decisions regarding freedom versus imprisonment, healing versus death, or justice versus discrimination. Their objective is to take the workload off decisionmakers and to enable them to make better informed decisions. However, in all these cases we want human agents, rather than intelligent systems, to make the final decision. This is because, first, only humans can take responsibility for decisions and, second, only humans can give appropriate weight to case-sensitive considerations in their decision-making processes. Intelligent systems therefore must be designed to assist us in deciding responsibly and in a wellinformed way. The project Explainable Intelligent Systems (EIS) thus needs a broad and interdisciplinary setup in order to answer its guiding research question: How can and should intelligent systems be designed to provide explainable recommendations? Although this problem is urgent, interdisciplinary research concerning the explainability of artificial intelligence is still in its infancy. While different disciplines have presented fragmentary results, a truly interdisciplinary research programme with a common language is still missing. This project aims to implement such a programme.

• Prof. Dr. Holger Hermanns

  Universität des Saarlandes
  Fakultät für Mathematik und Informatik
  Fachrichtung Informatik
  Lehrstuhl für Zuverlässige Systeme
  und Software
  Saarbrücken
  

• Dr. Eva Schmidt

  Universität Zürich
  Philosophische Fakultät
  Philosophie
  Institute of Philosophy
  Zürich
  Schweiz
  

• Prof. Dr. Ulla Wessels

  Universität des Saarlandes
  Philosophisches Institut
  Professur für Praktische Philosophie
  Saarbrücken
  

• Prof. Dr. Georg Borges

  Universität des Saarlandes
  Rechtswissenschaftliche Fakultät
  Professur für Bürgerliches Recht,
  Rechtsinformatik, deutsches und internationales
  Wirtschaftsrecht sowie Rechtstheorie
  Saarbrücken
  

• Prof. Dr. Cornelius König

  Universität des Saarlandes
  Fachrichtung Psychologie
  Professur für Arbeits- und
  Organisationspsychologie
  Saarbrücken
  

• What Do We Want From Explainable Artificial Intelligence (XAI) A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

• Where reasons and reasoning come apart

• Highly-Automated Job Interviews: Acceptance Under the Influence of Stakes

• Explainability as a Non-Functional Requirement