[论文解读] Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions

Luca Longo, Mario Brčić+17 more|arXiv (Cornell University)|Oct 30, 2023

Artificial Intelligence in Healthcare and Education参考文献 240被引用 14

一句话总结

一本合作性宣言，概述了横跨九个类别的27个开放XAI挑战，提出跨学科方向以推进可解释AI及其在现实世界的部署。

ABSTRACT

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.

研究动机与目标

• 综合来自不同领域的专家观点，识别XAI中的开放问题。
• 提出一个协同的跨学科研究议程，推动XAI 2.0。
• 突出可解释性在实际应用中的作用与现实意义。
• 提供跨领域与多方利益相关者之间研究协同的方向。

提出的方法

• 综合哲学、心理学、HCI和计算机科学领域的专家意见，以提取开放问题。
• 将问题组织成九个类别，包含27个具体挑战。
• 为每个问题提供拟议的研究方向和潜在解决方案方法。

Figure 1: A manifesto for eXplainable Artificial Intelligence (XAI): High-level challenges

实验结果

研究问题

• RQ1 由多学科小组识别出的XAI关键开放问题是什么？
• RQ2 如何在各学科之间同步XAI研究以加速现实世界的应用？
• RQ3 为生成式、基于概念的和鲁棒解释推进XAI 2.0提出了哪些方向和方法？

主要发现

• 将27个开放问题框定为XAI 2.0九大类别宣言。
• 强调解释新型AI类型（生成模型、基于概念的学习）以及改进现有XAI方法的挑战。
• 讨论XAI解释在评估、鲁棒性与以人为本的评估方面的差距。
• 举例说明包括医学、金融、环境和教育等应用领域，以促使跨学科工作。