Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Explainable Artificial Intelligence (XAI) 2.0
T2 - A manifesto of open challenges and interdisciplinary research directions
AU - Longo, Luca
AU - Brcic, Mario
AU - Cabitza, Federico
AU - Choi, Jaesik
AU - Confalonieri, Roberto
AU - Ser, Javier Del
AU - Guidotti, Riccardo
AU - Hayashi, Yoichi
AU - Herrera, Francisco
AU - Holzinger, Andreas
AU - Jiang, Richard
AU - Khosravi, Hassan
AU - Lecue, Freddy
AU - Malgieri, Gianclaudio
AU - Páez, Andrés
AU - Samek, Wojciech
AU - Schneider, Johannes
AU - Speith, Timo
AU - Stumpf, Simone
PY - 2024/2/17
Y1 - 2024/2/17
N2 - Understanding black box models has become paramount as systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its application in real-world scenarios and addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. We aim to develop a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 28 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.
AB - Understanding black box models has become paramount as systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its application in real-world scenarios and addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. We aim to develop a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 28 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.
KW - Explainable artificial intelligence
KW - XAI
KW - Interpretability
KW - Manifesto
KW - Open challenges
KW - Interdisciplinarity
KW - Ethical AI
KW - Large language models
KW - Trustworthy AI
KW - Responsible AI
KW - Generative AI
KW - Multi-faceted explanations
KW - Concept-based explanations
KW - Causality
KW - Actionable XAI
KW - Falsifiability
U2 - 10.1016/j.inffus.2024.102301
DO - 10.1016/j.inffus.2024.102301
M3 - Journal article
VL - 106
JO - Information Fusion
JF - Information Fusion
SN - 1566-2535
M1 - 102301
ER -