The XAI project contributes to an important manifesto published in Information Fusion(Longo et al., 2024) that defines future directions for research in eXplainable AI.
The article brings together experts from diverse fields to identify 27 open problems categorized into nine thematic areas. These challenges encapsulate the complexities and nuances of the XAI field and offer a roadmap for future research.
The manifesto highlights the need for broader perspectives and collaborative efforts to advance explainability, emphasizing the importance of addressing issues that go beyond mere accuracy toward a comprehensive understanding of model behavior in the specific contexts of their applications.
References
2024
Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions
Luca
Longo, Mario
Brcic, Federico
Cabitza, Jaesik
Choi, Roberto
Confalonieri, and
14 more authors
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also 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. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 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.
@article{LBC2024,author={Longo, Luca and Brcic, Mario and Cabitza, Federico and Choi, Jaesik and Confalonieri, Roberto and Ser, Javier Del and Guidotti, Riccardo and Hayashi, Yoichi and Herrera, Francisco and Holzinger, Andreas and Jiang, Richard and Khosravi, Hassan and Lecue, Freddy and Malgieri, Gianclaudio and Páez, Andrés and Samek, Wojciech and Schneider, Johannes and Speith, Timo and Stumpf, Simone},doi={10.1016/j.inffus.2024.102301},issn={1566-2535},journal={Information Fusion},line={1},month=jun,open_access={Gold},pages={102301},publisher={Elsevier BV},title={Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions},visible_on_website={YES},volume={106},year={2024}}
