Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability
This work addresses the problem of inadequate model documentation for improving accountability and preventing misuse in machine learning, though it is incremental as it builds on existing model card proposals.
The study identified a significant gap between the proposed model cards for machine learning documentation and actual practice, and developed DocML, a tool that nudges data scientists to comply with ethical sections, improving long-term documentation quality and accountability in a lab study.
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.