让数据溯源解释更贴近开发者真实需求
Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI
- 通过用户访谈和场景实验，从开发者视角重构数据溯源设计
- 发现分组模型行为对应样本、识别数据稀疏区域等新任务
- 适合关注可解释AI实用价值的研究者与人机交互从业者
可解释AI（XAI）旨在提升AI系统的透明度，但许多实践过于强调数学严谨性而忽视实际用户需求。本文提出一种以用户为中心的设计思维方法，应用于新兴的训练数据溯源（TDA）领域，避免重复其他子领域中固有的解决方案倾向。由于TDA尚处早期阶段，此时引入用户导向实践具有重要机遇。我们通过6名机器学习开发者的需因访谈和31名用户的场景化交互研究，将解释机制嵌入真实工作流。探索TDA设计空间后，揭示了对开发者有用的新任务，如将特定模型行为背后的训练样本进行分组，或识别数据覆盖不足的区域。本文呼吁TDA、XAI与人机交互社区共同关注这些任务，以增强研究的实践相关性和人文影响。
原文摘要 · Abstract (English)
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.
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。