Explainable and Ethical AI: A Perspective on Argumentation and Logic Programming

Roberta Calegari, Andrea Omicini, Giovanni Sartor

AIxIA 2020 – Advances in Artificial Intelligence, Ch. 2, pages 19–36
Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence) 12414, 2021
Springer Nature
Matteo Baldoni, Stefania Bandini (eds.)

In this paper we sketch a vision of explainability of intelligent systems as a logic approach suitable to be injected into and exploited by the system actors once integrated with sub-symbolic techniques.
In particular, we show how argumentation could be combined with different extensions of logic programming – namely, abduction, inductive logic programming, and probabilistic logic programming – to address the issues of explainable AI as well as some ethical concerns about AI.

(keywords) Explainable AI; Ethical AI; Argumentation; Logic programming; Abduction; Probabilistic LP; Inductive LP

@incollection{xaiethics-aiia2020,
author = {Calegari, Roberta and Omicini, Andrea and Sartor, Giovanni},
booktitle = {AIxIA 2020 -- Advances in Artificial Intelligence},
doi = {10.1007/978-3-030-73065-9_2},
editor = {Baldoni, Matteo and Bandini, Stefania},
isbn = {978-3-030-77090-7},
issn = {0302-9743},
keywords = {Explainable AI; Ethical AI; Argumentation; Logic programming; Abduction; Probabilistic LP; Inductive LP},
pages = {19--36},
publisher = {Springer Nature},
series = {Lecture Notes in Computer Science},
title = {Explainable and Ethical {AI}: A Perspective on Argumentation and Logic Programming},
url = {http://link.springer.com/10.1007/978-3-030-77091-4_2},
url-pdf = {http://link.springer.com/content/pdf/10.1007/978-3-030-77091-4_2.pdf},
volume = 12414,
year = 2021}

Journals & Series

Lecture Notes in Computer Science (LNCS)

Events

19th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2020) — 24/11/2020–27/11/2020