调研法律专家对AI解释的要求，助力符合欧盟隐私法规的可解释AI设计。
The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPR
- 通过问卷与访谈，研究法律专家对信用领域AI解释的期待。
- 发现现有解释难以理解且信息不足，存在数据控制方与个人利益冲突。
- 提出解释呈现、内容、技术风险等开发建议，适配法律合规需求。
可解释人工智能（XAI）提供了理解非可解释机器学习模型的方法。然而，我们对法律专家对这些解释的期望——包括其是否符合欧洲联盟立法——知之甚少。为填补这一空白，本文提出“解释对话”研究，通过在线问卷和后续访谈，探讨法律专家与从业者在信用领域使用案例中对XAI的期望、推理与理解。采用扎根理论提取层次化、相互关联的编码，呈现专家对XAI的立场。研究发现，当前解释难以理解且信息不全，并讨论了数据控制方与数据主体之间利益差异带来的问题。最后，面向XAI开发者提出多项建议，涵盖解释的呈现方式、选择与内容、技术风险及终端用户考量；同时提供法律层面的指引，涉及解释的可争议性、透明度阈值、知识产权以及各方关系。
原文摘要 · Abstract (English)
Explainable AI (XAI) provides methods to understand non-interpretable machine learning models. However, we have little knowledge about what legal experts expect from these explanations, including their legal compliance with, and value against European Union legislation. To close this gap, we present the Explanation Dialogues, an expert focus study to uncover the expectations, reasoning, and understanding of legal experts and practitioners towards XAI, with a specific focus on the European General Data Protection Regulation. The study consists of an online questionnaire and follow-up interviews, and is centered around a use-case in the credit domain. We extract both a set of hierarchical and interconnected codes using grounded theory, and present the standpoints of the participating experts towards XAI. We find that the presented explanations are hard to understand and lack information, and discuss issues that can arise from the different interests of the data controller and subject. Finally, we present a set of recommendations for developers of XAI methods, and indications of legal areas of discussion. Among others, recommendations address the presentation, choice, and content of an explanation, technical risks as well as the end-user, while we provide legal pointers to the contestability of explanations, transparency thresholds, intellectual property rights as well as the relationship between involved parties.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。