论文标题
模型文档的愿望和实践：用nuding和可追溯性移动针头
Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability
论文作者
论文摘要
机器学习的（ML）模型的文档实践通常缺乏传统软件的既定实践，这阻碍了模型问责制，并且无意中纳入了不适当或滥用模型的情况。最近，模型卡是模型文档的一项建议，引起了显着的关注，但是它们对实际实践的影响尚不清楚。在这项工作中，我们系统地研究了该领域的模型文档，并研究了如何鼓励更负责任和负责的文档实践。我们对公开可用模型卡的分析揭示了该提案与实践之间的巨大差距。然后，我们设计了一个名为DOCML的工具，旨在（1）推动数据科学家在模型开发过程中遵守模型卡建议，尤其是与道德有关的部分，以及（2）评估和管理文档质量。一项实验室研究揭示了我们工具对长期文档质量和问责制的好处。
The documentation practice for machine-learned (ML) models often falls short of established practices for traditional software, which impedes model accountability and inadvertently abets inappropriate or misuse of models. Recently, model cards, a proposal for model documentation, have attracted notable attention, but their impact on the actual practice is unclear. In this work, we systematically study the model documentation in the field and investigate how to encourage more responsible and accountable documentation practice. Our analysis of publicly available model cards reveals a substantial gap between the proposal and the practice. We then design a tool named DocML aiming to (1) nudge the data scientists to comply with the model cards proposal during the model development, especially the sections related to ethics, and (2) assess and manage the documentation quality. A lab study reveals the benefit of our tool towards long-term documentation quality and accountability.
