Using Knowledge Representation to achieve Reliable and trustworthy AI in Sensitive Infrastructure
Year: 2025
Type: conference-paper
Abstract: Artificial intelligence (AI) has become increasingly integrated into various aspects of society, from healthcare and finance to law enforcement and hiring processes, and more recently sensitive infrastructure such nuclear plants are trying to engage Artificial intelligence into aspect of safety. However, these systems are not immune to biases and ethical concerns. This paper explores the role of knowledge representation in addressing ethics and fairness in AI, examining how biased or incomplete representations can lead to unfair outcomes, unreliable decision making, and proposing strategies to mitigate these risks.
Authors: Oumayma, Mejri, Waedt, Karl, Yatagha, Romarick, Ruland, Karl Christoph, Zeddini, Oumayma
Institutions: Framatome (Germany), University of Siegen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7108482007