系统梳理可解释AI的原理、方法与应用，助力提升AI透明度与可信度。
Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
- 构建XAI技术分类体系，涵盖模型内部解释与外部代理方法。
- 分析医疗、金融等高风险领域对可解释性的迫切需求。
- 为研究者与开发者提供提升AI公平性与责任性的实践指引。
人工智能模型因黑箱特性在医疗、金融、自动驾驶等安全关键领域面临严峻挑战。可解释人工智能（XAI）通过揭示模型决策过程，保障透明性、可问责性与公平性。现有研究虽涵盖XAI基础概念与通用原则，但缺乏对数学表征、设计方法等深层细节的系统综述。本文全面回顾了XAI的术语定义、必要性、受益群体、方法分类及应用场景，涵盖模型内解释与模型外解释等主流技术路径。研究旨在为XAI研究人员、从业者、模型开发者及使用者提供增强模型可信度、透明性与公平性的理论与实践参考。
原文摘要 · Abstract (English)
Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models.
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。