AEQUITAS 2023
Fairness and Bias in AI

Table of Contents

• Preface
  Summary: There were 13 papers submitted for peer-review to this workshop. Out of these, 12 papers were accepted for this volume, 12 as regular papers and 0 as short papers.

Papers

• Causal Fair Machine Learning via Rank-Preserving Interventional Distributions
  Ludwig Bothmann, Susanne Dandl, Michael Schomaker
• Visualizing Bias in Activations of Deep Neural Networks as Topographic Maps
  Valerie Krug, Christopher Olson, Sebastian Stober
• Recommendations for Bias Mitigation Methods: Applicability and Legality
  Madeleine Waller, Odinaldo Rodrigues, Oana Cocarascu
• Reasoning With Bias
  Chiara Manganini, Giuseppe Primiero
• FAiRDAS: Fairness-Aware Ranking as Dynamic Abstract System
  Eleonora Misino, Roberta Calegari, Michele Lombardi, Michela Milano
• EXTRACT: Explainable Transparent Control of Bias in Embeddings
  Zhijin Guo, Zhaozhen Xu, Martha Lewis, Nello Cristianini
• Fairness in job recommendations: estimating, explaining, and reducing gender gaps
  Guillaume Bied, Christophe Gaillac, Morgane Hoffmann, Philippe Caillou, Bruno Crépon, Solal Nathan, Michèle Sebag,
• Gender Bias in Multimodal Models: A Transnational Feminist Approach Considering Geographical Region and Culture
  Abhishek Mandal, Suzanne Little, Susan Leavy
• A geometric framework for fairness
  Alessandro Maggio, Luca Giuliani, Roberta Calegari, Michele Lombardi, Michela Milano
• Symbolic AI (LFIT) for XAI to handle biases
  Javier Tello, Marina de la Cruz, Tony Ribeiro, Julian Fierrez, Aythami Morales, Ruben Tolosana, César Luis Alonso, Alfonso Ortega
• Bias Mitigation for Large Language Models using Adversarial Learning
  Jasmina S. Ernst, Sascha Marton, Jannik Brinkmann, Eduardo Vellasques, Damien Foucard, Martin Kraemer, Marian Lambert
• Impact based fairness framework for socio-technical decision making
  Mattias Brännström, Lili Jiang, Andrea Aler Tubella, Virginia Dignum