A review of taxonomies of explainable artificial intelligence (XAI) methods
T Speith - Proceedings of the 2022 ACM conference on fairness …, 2022 - dl.acm.org
The recent surge in publications related to explainable artificial intelligence (XAI) has led to
an almost insurmountable wall if one wants to get started or stay up to date with XAI. For this …
an almost insurmountable wall if one wants to get started or stay up to date with XAI. For this …
[HTML][HTML] Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions
Understanding black box models has become paramount as systems based on opaque
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …
From responsibility to reason-giving explainable artificial intelligence
We argue that explainable artificial intelligence (XAI), specifically reason-giving XAI, often
constitutes the most suitable way of ensuring that someone can properly be held …
constitutes the most suitable way of ensuring that someone can properly be held …
On the relation of trust and explainability: Why to engineer for trustworthiness
Recently, requirements for the explainability of software systems have gained prominence.
One of the primary motivators for such requirements is that explainability is expected to …
One of the primary motivators for such requirements is that explainability is expected to …
A new perspective on evaluation methods for explainable artificial intelligence (xai)
One of the big challenges in the field of explainable artificial intelligence (XAI) is how to
evaluate explainability approaches. Many evaluation methods (EMs) have been proposed …
evaluate explainability approaches. Many evaluation methods (EMs) have been proposed …
Engineering ethical behaviors in autonomous industrial cyber-physical human systems
D Trentesaux, S Karnouskos - Cognition, Technology & Work, 2022 - Springer
This paper addresses the engineering of the ethical behaviors of autonomous industrial
cyber-physical human systems in the context of Industry 4.0. An ethical controller is …
cyber-physical human systems in the context of Industry 4.0. An ethical controller is …
Explainability auditing for intelligent systems: a rationale for multi-disciplinary perspectives
National and international guidelines for trustworthy artificial intelligence (AI) consider
explainability to be a central facet of trustworthy systems. This paper outlines a multi …
explainability to be a central facet of trustworthy systems. This paper outlines a multi …
How to evaluate explainability?-a case for three criteria
T Speith - 2022 IEEE 30th International Requirements …, 2022 - ieeexplore.ieee.org
The increasing complexity of software systems and the influence of software-supported
decisions in our society have sparked the need for software that is safe, reliable, and fair …
decisions in our society have sparked the need for software that is safe, reliable, and fair …
Moral dilemmas for moral machines
T LaCroix - AI and Ethics, 2022 - Springer
Autonomous systems are being developed and deployed in situations that may require
some degree of ethical decision-making ability. As a result, research in machine ethics has …
some degree of ethical decision-making ability. As a result, research in machine ethics has …
Metaethical perspectives on'Benchmarking'AI ethics
T LaCroix, AS Luccioni - arXiv preprint arXiv:2204.05151, 2022 - arxiv.org
Benchmarks are seen as the cornerstone for measuring technical progress in Artificial
Intelligence (AI) research and have been developed for a variety of tasks ranging from …
Intelligence (AI) research and have been developed for a variety of tasks ranging from …