[论文解读] Explainable AI is Responsible AI: How Explainability Creates Trustworthy and Socially Responsible Artificial Intelligence

Stephanie Baker, Wei Xiang|arXiv (Cornell University)|Dec 4, 2023

Ethics and Social Impacts of AI被引用 12

一句话总结

本文主张可解释性人工智能（XAI）是负责人工智能（RAI）的基础性技术，在各个情境中促成公平性、鲁棒性、隐私、安全和透明度，并提出一个新颖框架及现实世界的用例。

ABSTRACT

Artificial intelligence (AI) has been clearly established as a technology with the potential to revolutionize fields from healthcare to finance - if developed and deployed responsibly. This is the topic of responsible AI, which emphasizes the need to develop trustworthy AI systems that minimize bias, protect privacy, support security, and enhance transparency and accountability. Explainable AI (XAI) has been broadly considered as a building block for responsible AI (RAI), with most of the literature considering it as a solution for improved transparency. This work proposes that XAI and responsible AI are significantly more deeply entwined. In this work, we explore state-of-the-art literature on RAI and XAI technologies. Based on our findings, we demonstrate that XAI can be utilized to ensure fairness, robustness, privacy, security, and transparency in a wide range of contexts. Our findings lead us to conclude that XAI is an essential foundation for every pillar of RAI.

研究动机与目标

• 在多项支柱（公平、鲁棒性、透明度、问责、隐私、安全）中的RAI框架中确立XAI的作用。
• 提出一个框架，将可解释性定位为RAI的基础，而不是单一支柱。
• 综合证据，展示XAI如何支持RAI的支柱并在现实世界用例中实现改进。
• 通过行业聚焦的用例（生成式AI、医疗、交通）演示XAI在实践中如何直接支持RAI。

提出的方法

• 对XAI与RAI文献进行广泛范围的综述。
• 提出一个新颖框架，将可解释性作为RAI的基础。
• 严格的探讨表明XAI支撑公平、鲁棒性、隐私、安全、透明度和问责。
• 在生成式AI、医疗保健和交通领域展示现实世界用例，以证明实际影响。

Figure 1 . Comparison of RAI frameworks (a) as commonly defined in the literature with explainability as a pillar, and (b) as proposed by this work with explainability as the foundational concept.

实验结果

研究问题

• RQ1 如何将可解释性AI概念化为负责任AI的基础而非单一支柱？
• RQ2 XAI文献中的哪些证据证明其对RAI中的公平、鲁棒性、隐私、安全和透明度的贡献？
• RQ3 如何将XAI应用于现实世界的用例，以提升AI系统的可信性与社会责任？
• RQ4 当XAI被视为RAI的基础时，对未来AI研究与部署有哪些建议？

主要发现

• XAI可以支持并增强所有RAI支柱：公平、鲁棒性、隐私、安全、透明度和问责。
• XAI提供透明度，提升可解释性和理解力，帮助如金融和法律等领域的问责。
• XAI可以与隐私保护技术结合，以满足隐私要求，而不影响其他RAI需求。
• 作者提出XAI应成为RAI的基础，而不仅是一个独立支柱，并以现实世界用例来说明。
• 该工作通过在统一框架中连接XAI与RAI并强调在医疗、交通和生成式AI中的实际应用，填补了这一空白。

Figure 2 . Overview of the key contents of this paper