Fairness implications of encoding protected categorical attributes
C Mougan, JM Álvarez, S Ruggieri… - Proceedings of the 2023 …, 2023 - dl.acm.org
Past research has demonstrated that the explicit use of protected attributes in machine
learning can improve both performance and fairness. Many machine learning algorithms …
learning can improve both performance and fairness. Many machine learning algorithms …
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 …
When Causality Meets Fairness: A Survey
Addressing the problem of fairness is crucial to safely using machine learning algorithms to
support decisions that have a critical impact on people's lives, such as job hiring, child …
support decisions that have a critical impact on people's lives, such as job hiring, child …
Bias-aware ranking from pairwise comparisons
Human feedback is often used, either directly or indirectly, as input to algorithmic decision
making. However, humans are biased: if the algorithm that takes as input the human …
making. However, humans are biased: if the algorithm that takes as input the human …
Causal Perception
JM Alvarez, S Ruggieri - arXiv preprint arXiv:2401.13408, 2024 - arxiv.org
Perception occurs when two individuals interpret the same information differently. Despite
being a known phenomenon with implications for bias in decision-making, as individuals' …
being a known phenomenon with implications for bias in decision-making, as individuals' …
Uncovering Algorithmic Discrimination: An Opportunity to Revisit the Comparator
JM Alvarez, S Ruggieri - arXiv preprint arXiv:2405.13693, 2024 - arxiv.org
Causal reasoning, in particular, counterfactual reasoning plays a central role in testing for
discrimination. Counterfactual reasoning materializes when testing for discrimination, what …
discrimination. Counterfactual reasoning materializes when testing for discrimination, what …
Formalising Anti-Discrimination Law in Automated Decision Systems
H Sargeant, M Magnusson - arXiv preprint arXiv:2407.00400, 2024 - arxiv.org
We study the legal challenges in automated decision-making by analysing conventional
algorithmic fairness approaches and their alignment with antidiscrimination law in the United …
algorithmic fairness approaches and their alignment with antidiscrimination law in the United …
What's the Problem, Linda? The Conjunction Fallacy as a Fairness Problem
JA Colmenares - arXiv preprint arXiv:2305.09535, 2023 - arxiv.org
The field of Artificial Intelligence (AI) is focusing on creating automated decision-making
(ADM) systems that operate as close as possible to human-like intelligence. This effort has …
(ADM) systems that operate as close as possible to human-like intelligence. This effort has …
Trustworthy machine learning: mitigating bias and promoting fairness in automated decision systems
S Wolters - 2023 - oa.upm.es
The widespread adoption of Artificial Intelligence (AI) and Machine Learning (ML) algorithms
in recent years across many domains has led to an increased reliance on automated …
in recent years across many domains has led to an increased reliance on automated …