面向以用户为中心的可解释AI训练数据归因研究
Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI
AI总结：
本研究针对可解释AI训练数据归因（TDA）领域忽视用户需求的问题，通过访谈和交互式用户研究直接与开发者合作，提出以用户为中心的设计思维方法，揭示了对开发者有用的以数据为中心的解释新任务，增强研究的实用性和人类影响。
摘要：
可解释AI（XAI）旨在使AI系统更加透明，但许多实践强调数学严谨性而忽视实际用户需求。我们提出一种替代这种以模型为中心的方法，遵循设计思维流程应用于新兴的XAI领域——训练数据归因（TDA），该领域存在重蹈其他子领域技术解决方案主义覆辙的风险。然而，由于TDA仍处于早期阶段，通过以用户为中心的实践来塑造其方向具有宝贵机会。我们通过需求发现访谈研究（N=6）和基于场景的交互式用户研究（N=31）直接与机器学习开发者互动，将解释扎根于真实工作流程。我们对TDA设计空间的探索揭示了对开发者有用的以数据为中心的解释新任务，例如对特定模型行为背后的训练样本进行分组，或识别采样不足的数据。我们邀请TDA、XAI和HCI社区参与这些任务，以增强其研究的实用相关性和人类影响。
英文摘要：
Explainable AI (XAI) aims to make AI systems more transparent, yet many practices emphasise mathematical rigour over practical user needs. We propose an alternative to this model-centric approach by following a design thinking process for the emerging XAI field of training data attribution (TDA), which risks repeating solutionist patterns seen in other subfields. However, because TDA is in its early stages, there is a valuable opportunity to shape its direction through user-centred practices. We engage directly with machine learning developers via a needfinding interview study (N=6) and a scenario-based interactive user study (N=31) to ground explanations in real workflows. Our exploration of the TDA design space reveals novel tasks for data-centric explanations useful to developers, such as grouping training samples behind specific model behaviours or identifying undersampled data. We invite the TDA, XAI, and HCI communities to engage with these tasks to strengthen their research's practical relevance and human impact.
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。
