collaborators

6 papers

cs.LG2025

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

Loukas Kavouras, Eleni Psaroudaki, Konstantinos Tsopelas +9

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods…

cs.LG2025

Source Attribution in Retrieval-Augmented Generation

Ikhtiyor Nematov, Tarik Kalai, Elizaveta Kuzmenko +4

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Larg…

cs.LG2024

AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations

Ikhtiyor Nematov, Dimitris Sacharidis, Tomer Sagi +1

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customi…

cs.LG2024

The Susceptibility of Example-Based Explainability Methods to Class Outliers

Ikhtiyor Nematov, Dimitris Sacharidis, Tomer Sagi +1

This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explain…

cs.CY2024

Fairness in AI: challenges in bridging the gap between algorithms and law

Giorgos Giannopoulos, Maria Psalla, Loukas Kavouras +4

In this paper we examine algorithmic fairness from the perspective of law aiming to identify best practices and strategies for the specification and adoption of fairness definition…

cs.LG2024

FALE: Fairness-Aware ALE Plots for Auditing Bias in Subgroups

Giorgos Giannopoulos, Dimitris Sacharidis, Nikolas Theologitis +2

Fairness is steadily becoming a crucial requirement of Machine Learning (ML) systems. A particularly important notion is subgroup fairness, i.e., fairness in subgroups of individua…