BEWARE 2023
Bias, Ethical AI, Explainability and the role of Logic and Logic Programming

Table of Contents

• Preface
  Summary: There were 11 papers submitted for peer-review to this workshop. Out of these, 9 papers were accepted for this volume, 5 as regular papers and 4 as short papers.

Regular Papers

• Unveiling Opaque Predictors via Explainable Clustering: The CReEPy Algorithm 1-14
  Federico Sabbatini , Roberta Calegari
• Bridging Human Concepts and Computer Vision for Explainable Face Verification 15-29
  Miriam Doh , Caroline Mazini Rodrigues , Nicolas Boutry , Laurent Najman , Matei Mancas , Hugues Bersini
• Exploring Ethical and Conceptual Foundations of Human-Centred Symbiosis with Artificial Intelligence 30-43
  Antonio Carnevale , Antonio Lombardi , Francesca Alessandra Lisi
• BRIOxAlkemy: a Bias Detecting Tool 44-60
  Greta Coraglia , Fabio Aurelio D'Asaro , Francesco Antonio Genco , Davide Giannuzzi , Davide Posillipo , Giuseppe Primiero , Christian Quaggio
• Towards a Logical Foundation of Randomized Computation 61-72
  Melissa Antonelli

Short Papers

• An Italian Dataset for the Analysis of Gender Stereotypes in Textual Documents 73-78
  Silvana Badaloni , Antonio Rodà , Martino Scagnet
• An XAI-Based Masking Approach to Improve Classification Systems 79-83
  Andrea Apicella , Salvatore Giugliano , Francesco Isgrà , Andrea Pollastro , Roberto Prevete
• Inductive Logic Programming for Transparent Alignment with Multiple Moral Values 84-88
  Celeste Veronese , Daniele Meli , Filippo Bistaffa , Manel Rodríguez-Soto , Alessandro Farinelli , Juan A. Rodríguez-Aguilar
• A Logical Approach to Algorithmic Opacity 89-95
  Mattia Petrolo , Ekaterina Kubyshkina , Giuseppe Primiero