ePrints

How Explainable Really Is AI? Benchmarking Explainable AI

Lookup NU author(s): Dr Giacomo BergamiORCiD, Ollie Fox

Downloads

• Published version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

This work contextualizes the possibility of deriving a unifying artificial intelligence framework by walking in the footsteps of General, Explainable, and Verified Artificial Intelligence (GEVAI): by considering explainability not only at the level of the results produced by a specification but also considering the explicability of the inference process as well as the one related to the data processing step, we can not only ensure human explainability of the process leading to the ultimate results but also mitigate and minimize machine faults leading to incorrect results. This, on the other hand, requires the adoption of automated verification processes beyond system fine-tuning, which are essentially relevant in a more interconnected world. The challenges related to full automation of a data processing pipeline, mostly requiring human-in-the-loop approaches, forces us to tackle the framework from a different perspective: while proposing a preliminary implementation of GEVAI mainly used as an AI test-bed having different state-of-the-art AI algorithms interconnected, we propose two other data processing pipelines, LaSSI and EMeriTAte+DF, being a specific instantiation of GEVAI for solving specific problems (Natural Language Processing, and Multivariate Time Series Classifications). Preliminary results from our ongoing work strengthen the position of the proposed framework by showcasing it as a viable path to improve current state-of-the-art AI algorithms.

Publication metadata

Author(s): Bergami G, Fox OR

Publication type: Article

Publication status: Published

Journal: Logics

Year: 2025

Volume: 3

Issue: 3

Online publication date: 06/08/2025

Acceptance date: 24/07/2025

Date deposited: 20/08/2025

ISSN (electronic): 2813-0405

Publisher: MDPI

URL: https://doi.org/10.3390/logics3030009

DOI: 10.3390/logics3030009

Data Access Statement: The preliminary release of the GEVAI project is available at: https://github.com/LogDS/GEVAI (accessed on 28 July 2025). Result data can be found at: https://osf.io/6jf5z/?view_only=112ebdd0156444ddbb8cf6ea53729949 (accessed on 28 July 2025).

Altmetrics

Share