Efstratios Zaradoukas

2 accepted papers

2026

Reinforcement Unlearning via Group Relative Policy Optimization

Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

ICLR 2026poster

During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove information from a deployed model without retraining from scrat…

Cited by 0 Source ↗Scholar ↗

2025

Graph Inverse Style Transfer for Counterfactual Explainability

Bardh Prenkaj, Efstratios Zaradoukas, Gjergji Kasneci

ICML 2025poster

Counterfactual explainability seeks to uncover model decisions by identifying minimal changes to the input that alter the predicted outcome. This task becomes particularly challenging for graph data due to preserving structural integrity and semantic meaning. Unlike prior approaches that rely on for…

Cited by 0 Source ↗PDF ↗Scholar ↗