Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
In this work, we study the effects of feature-based explanations on distributive fairness of AI-
assisted decisions, specifically focusing on the task of predicting occupations from short …
assisted decisions, specifically focusing on the task of predicting occupations from short …
Mapping the Potential of Explainable Artificial Intelligence (XAI) for Fairness Along the AI Lifecycle
The widespread use of artificial intelligence (AI) systems across various domains is
increasingly highlighting issues related to algorithmic fairness, especially in high-stakes …
increasingly highlighting issues related to algorithmic fairness, especially in high-stakes …
Policy advice and best practices on bias and fairness in AI
JM Alvarez, AB Colmenarejo, A Elobaid… - Ethics and Information …, 2024 - Springer
The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace,
making it difficult for novel researchers and practitioners to have a bird's-eye view picture of …
making it difficult for novel researchers and practitioners to have a bird's-eye view picture of …
To err is human: Bias salience can help overcome resistance to medical AI
Prior research has shown that many individuals exhibit an aversion to algorithms and are
resistant to the use of artificial intelligence (AI) in healthcare. In the present research, we …
resistant to the use of artificial intelligence (AI) in healthcare. In the present research, we …
Conceptualizing understanding in explainable artificial intelligence (XAI): an abilities-based approach
T Speith, B Crook, S Mann, A Schomäcker… - Ethics and Information …, 2024 - Springer
A central goal of research in explainable artificial intelligence (XAI) is to facilitate human
understanding. However, understanding is an elusive concept that is difficult to target. In this …
understanding. However, understanding is an elusive concept that is difficult to target. In this …
Why Do Tree Ensemble Approximators Not Outperform the Recursive-Rule eXtraction Algorithm?
S Onishi, M Nishimura, R Fujimura… - Machine Learning and …, 2024 - mdpi.com
Although machine learning models are widely used in critical domains, their complexity and
poor interpretability remain problematic. Decision trees (DTs) and rule-based models are …
poor interpretability remain problematic. Decision trees (DTs) and rule-based models are …
How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law
B Fresz, E Dubovitskaya, D Brajovic, M Huber… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper investigates the relationship between law and eXplainable Artificial Intelligence
(XAI). While there is much discussion about the AI Act, for which the trilogue of the European …
(XAI). While there is much discussion about the AI Act, for which the trilogue of the European …
Explainability and Transparency in Practice: A Comparison Between Corporate and National AI Ethics Guidelines in Germany and China
T Speith, J Xu - … on Explainable, Transparent Autonomous Agents and …, 2024 - Springer
As artificial intelligence (AI) continues to permeate various sectors, ethical concerns,
particularly around transparency and explainability, have grown. While research has …
particularly around transparency and explainability, have grown. While research has …
Implications of the AI Act for Non-Discrimination Law and Algorithmic Fairness
L Deck, JL Müller, C Braun, D Zipperling… - arXiv preprint arXiv …, 2024 - arxiv.org
The topic of fairness in AI, as debated in the FATE (Fairness, Accountability, Transparency,
and Ethics in AI) communities, has sparked meaningful discussions in the past years …
and Ethics in AI) communities, has sparked meaningful discussions in the past years …
FairAD-XAI: Evaluation Framework for Explainable AI Methods in Alzheimer's Disease Detection with Fairness-in-the-loop
Despite significant progress in model developments, evaluating eXplainable Artificial
Intelligence (XAI) remains elusive and challenging in Alzheimer's Disease (AD) detection …
Intelligence (XAI) remains elusive and challenging in Alzheimer's Disease (AD) detection …