迈向以人为中心的可解释AI：关于模型解释的用户研究综述
Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
AI总结：
本文系统回顾了过去五年97篇XAI用户研究核心论文，按信任、理解、可用性和人机协作性能分类，发现用户评估稀少且缺乏认知科学见解，并提出了实用指南和未来研究方向。
摘要：
可解释AI（XAI）被广泛认为是不断扩展的AI研究的必要条件。了解XAI用户的需求，以及对可解释模型进行以人为中心的评估，既是必然要求也是一项挑战。本文基于系统的文献回顾，探讨了HCI和AI研究人员如何在XAI应用中开展用户研究。我们在过去五年中识别并深入分析了97篇包含基于人的XAI评估的核心论文，并沿着解释方法的测量特征对它们进行分类，即信任、理解、可用性和人机协作性能。研究表明，XAI在某些应用领域（如推荐系统）中比其他领域传播得更快，但用户评估仍然相当稀少，且几乎没有纳入认知科学或社会科学的见解。基于对最佳实践（即用户研究中常见的模型、设计选择和测量方法）的全面讨论，我们为XAI研究人员和从业者提出了设计和开展用户研究的实用指南。最后，本综述还强调了几个开放的研究方向，特别是将心理科学与以人为中心的XAI联系起来。
英文摘要：
Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how HCI and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 97core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, usability, and human-AI collaboration performance. Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.
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。
