Vol-3319
urn:nbn:de:0074-3319-5

Copyright © 2022 for the individual papers by the papers' authors. Copyright © 2022 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).

BEWARE 2022
Bias, Ethical AI, Explainability and the Role of Logic and Logic Programming

Proceedings of 1st Workshop on Bias, Ethical AI, Explainability and the Role of Logic and Logic Programming (BEWARE 2022)
co-located with the 21th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2022)

Udine, Italy, December 2, 2022.

Edited by

Guido Boella *
Fabio Aurelio D'Asaro
Abeer Dyoub *
Giuseppe Primiero ****

* University of Turin, Department of Computer Science, Turin, Italy
** University of Verona, Ethos Group, Department of Human Sciences, Verona, Italy
*** University of L'Aquila, DISIM, L'Aquila, Italy
**** University of Milan, LUCI Group, Department of Philosophy, Milan, Italy

Table of Contents

Preface
Summary: There were 14 papers submitted for peer-review to this workshop. Out of these, 13 papers were accepted for this volume, 4 as regular papers and 9 as short papers.

Invited Talk

Ethics and Gender for Responsible Research and Innovation in AI (extended abstract) 1-8
Francesca Alessandra Lisi

Session 1: Logic For AI

Proof-checking Bias in Labeling Methods 9-19
Giuseppe Primiero, Fabio Aurelio D'Asaro
Two Remarks on Counting Propositional Logic 20-32
Melissa Antonelli
Logics for Binary-input Classifiers and Their Explanations (short paper) 33-38
Xinghan Liu, Emiliano Lorini
Reasoning About Algorithmic Opacity (short paper) 39-45
Mattia Petrolo, Ekaterina Kubyshkina

Session 2: Technical Approaches to XAI

Investigating Bias with a Synthetic Data Generator: Empirical Evidence and Philosophical Interpretation 46-60
Alessandro Castelnovo, Riccardo Crupi, Nicole Inverardi, Daniele Regoli, Andrea Cosentini
Fairness and Bias in Learning Systems: a Generative Perspective (short paper) 61-66
Serge Dolgikh
Using Inductive Logic Programming to Globally Approximate Neural Networks for Preference Learning: Challenges and Preliminary Results 67-83
Daniele Fossemò, Filippo Mignosi, Luca Raggioli, Matteo Spezialetti, Fabio D'Asaro
XAI Approach for Addressing the Dataset Shift Problem: BCI as a Case Study (short paper) 83-88
Andrea Apicella, Francesco Isgrò, Roberto Prevete
Investigation and Mitigation of Bias in Explainable AI (short paper) 89-94
Muhammad Suffian, Alessandro Bogliolo

Session 3: Conceptual Views

Explaining Predictions with Enthymematic Counterfactuals (short paper) 95-100
Alexander Berman, Ellen Breitholtz, Christine Howes, Jean-Philippe Bernardy
XAI and Philosophical Work on Explanation: a Survey (short paper) 101-106
Aleks Knoks, Thomas Raleigh
Gender Knowledge and Artificial Intelligence (short paper) 107-112
Silvana Badaloni, Antonio Rodà

2023-01-06: submitted by Fabio Aurelio D'Asaro, metadata incl. bibliographic data published under Creative Commons CC0
2023-01-08: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|