可解释生成式AI（GenXAI）：综述、概念化与研究议程
Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda
AI总结：
该综述阐述了生成式AI（GenAI）兴起下可解释性（XAI）的重要性与挑战，梳理现有研究、提出分类体系与实现路径，并给出十余项未来研究方向，兼顾技术与非技术读者。
摘要：
生成式AI（GenAI）标志着AI从具备识别能力转向能够为各类任务生成解决方案。随着生成的解决方案与应用变得愈发复杂多元，可解释性（XAI）领域出现了新的需求、目标与可能性。本研究阐述了XAI为何随GenAI的兴起愈发重要，以及它给可解释性研究带来的挑战。我们还揭示了解释应当满足的新兴关键需求，涵盖可验证性、交互性、安全性与成本等方面。为此，我们重点梳理了现有相关研究，还提出了相关维度的分类体系，以更好地刻画现有面向GenAI的XAI机制与方法的特征。我们讨论了实现XAI的不同路径，覆盖从训练数据到提示工程的各环节。本文为非技术读者提供了简洁的GenAI技术背景，聚焦文本与图像领域，以帮助理解面向GenAI的新型或适配型XAI技术。不过，鉴于GenAI领域研究数量庞大，我们决定暂不深入探讨与解释的评估及使用相关的XAI细节。因此，本文既适合技术导向的研究者，也能惠及社会科学、信息系统研究等其他学科的从业者。我们提出的研究路线图给出了十余项未来研究方向。
英文摘要：
Generative AI (GenAI) marked a shift from AI being able to recognize to AI being able to generate solutions for a wide variety of tasks. As the generated solutions and applications become increasingly more complex and multi-faceted, novel needs, objectives, and possibilities have emerged for explainability (XAI). In this work, we elaborate on why XAI has gained importance with the rise of GenAI and its challenges for explainability research. We also unveil novel and emerging desiderata that explanations should fulfill, covering aspects such as verifiability, interactivity, security, and cost. To this end, we focus on surveying existing works. Furthermore, we provide a taxonomy of relevant dimensions that allows us to better characterize existing XAI mechanisms and methods for GenAI. We discuss different avenues to ensure XAI, from training data to prompting. Our paper offers a short but concise technical background of GenAI for non-technical readers, focusing on text and images to better understand novel or adapted XAI techniques for GenAI. However, due to the vast array of works on GenAI, we decided to forego detailed aspects of XAI related to evaluation and usage of explanations. As such, the manuscript interests both technically oriented people and other disciplines, such as social scientists and information systems researchers. Our research roadmap provides more than ten directions for future investigation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
