Counterfactual Explanation at Will, with Zero Privacy Leakage

S An, Y Cao - Proceedings of the ACM on Management of Data, 2024 - dl.acm.org
While counterfactuals have been extensively studied as an intuitive explanation of model
predictions, they still have limited adoption in practice due to two obstacles:(a) They rely on …

Drawing Attributions From Evolved Counterfactuals

J Jakubik, H Kwaśnicka - Proceedings of the Genetic and Evolutionary …, 2024 - dl.acm.org
eXplainable Artificial intelligence (XAI) has grown in popularity in recent years due to the
great demand for black-box machine learning models, particularly deep neural networks …

[KÖNYV][B] Auditing the Ranking Strategy of a Marketplace's Algorithm in the Frame of Competition Law Commitments with Surrogate Models: The Amazon's Buy Box …

J Mouton, B Rottembourg - 2024 - 195.220.190.85
In a global context where competition authorities are investigating and sanctioning
Amazon's marketplace for practices of self-preferencing at the expense of their business …

Reasoning With and About Bias

C Manganini, G Primiero - Perspectives on Logics for Data-driven …, 2024 - Springer
The widespread emergence of phenomena of bias is certainly among the most adverse
impacts of new data-intensive sciences and technologies. The causes of such undesirable …

[PDF][PDF] Tree Models for Interpretable Agents

T Bewley, T Bewley - AI (expert), 2012 - research-information.bris.ac.uk
As progress in AI impacts all sectors of society, the world is destined to see increasingly
complex and numerous autonomous decision-making agents, which act upon their …