“explainable AI” papers · AI for Research

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.

Cited by 0Open access

How Explainable Really Is AI? Benchmarking Explainable AI

Giacomo Bergami, Oliver Robert Fox · Logics · 2025

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.

Cited by 0Open access

SLR Explainable AI

Jerónimo Paiva · Figshare · 2026

Literature Review

Cited by 0Open access

Envisioning Explainable AI

K. Chakrapani, Mohamed Iqubal Safa, Sruthi M. Krishna Moorthy et al. · 2025

Artificial intelligence (AI) has permeated diverse sectors necessitating transparency in its decision-making processes. Explainable AI (XAI) emerged to address this need providing clarity into AI systems’ operations and bolstering user trust. This chapter explores XAI's transformative influence across industries like healthcare, finance, and autonomous systems. By elucidating core XAI concepts and methodologies, we uncover how XAI fosters transparency, aids decision-making in medicine, drives policy alterations, promotes fairness in evaluations, and ensures the safety of autonomous technologies like vehicles and drones. Additionally, we scrutinize the regulatory and disciplinary mechanisms implemented by XAI to safeguard privacy and ensure accountability. Despite challenges, XAI signifies a shift toward a future where AI systems are not only accountable and transparent but also harmonized with societal norms. Its potential lies in reshaping regulations, refining user experiences, and mitigating biases. As XAI advances, it holds the promise of a more transparent, equitable, and responsible AI landscape, where human–AI collaboration flourishes bolstering trust and acceptance in AI technologies.

Cited by 1Open access

SLR Explainable AI

Jerónimo Paiva · Open MIND · 2026

Literature Review

Cited by 0Open access

Explainable Commonsense AI

Filip Ilievski · Synthesis lectures on computer science · 2024

Cited by 0

Search 250 million research papers