AEQUITAS 2025
Fairness and Bias in AI

Table of Contents

• Summary: There were 27 papers submitted for peer-review to this workshop. Out of these, 14 papers were accepted for this volume, 14 as regular papers and 0 as short papers.

Papers

• Modeling Fairness in Recruitment AI via Information Flow
  Mattias Brännström, Themis Dimitra Xanthopoulou, Lili Jiang
• VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation
  Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
• Transparency and Proportionality in Post-Processing Algorithmic Bias Correction
  Juliett Suárez-Ferreira, Marija Slavkovik, Jorge Casillas
• Causal Synthetic Data Generation in Recruitment
  Andrea Iommi, Antonio Mastropietro, Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri
• A Fairness-Oriented Visual Extension for the PSyKE Platform
  Federico Sabbatini
• Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models
  Riccardo Cantini, Nicola Gabriele, Alessio Orsino, Domenico Talia
• First Ask Then Act (FATA): A Community-Centered Inclusive Approach for Hate Speech Detection
  Chiara Ferrando, Lia Draetta, Andrea Marra, Angela Zottola, Cristina Bosco, Viviana Patti
• How do doctors perceive AI in their medical practice?
  Laura Sartori, Chiara Binelli, Francesca Lizzi, Andrea Chincarini, Francesco Sensi, Alessandra Retico
• On the Correlation between Individual Fairness and Predictive Accuracy in Probabilistic Models
  Alessandro Antonucci, Eric Rossetto, Ivan Duvnjak
• Towards a Partial Coverage of Neural Network Explanations Using Approximation Networks
  Mathieu Brassart, Laurent Simon
• Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space
  Sofoklis Kitharidis, Cor J. Veenman, Thomas Bäck, Niki van Stein
• Evaluating and Mitigating Fairness Risks in Machine Learning under Structured Missing Data
  Tim Kochs, Andrea Castellani, Felix Lanfermann, Barbara Hammer
• Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
  Katharina Simbeck, Mariam Mahran
• Bias Detection in Cultural Heritage Metadata: Preliminary Results from the IMAGES Project
  Angelo Oddi, Gianmauro Romagna, Riccardo Rasconi, Paola Panarese, Paolo De Gasperis