Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability

TL;DR

This paper examines the current state of model documentation practices, identifies gaps between proposals and actual use, and introduces a tool called DocML to promote responsible documentation and improve accountability in ML models.

Contribution

The paper provides a systematic analysis of model card adoption, identifies gaps, and introduces DocML, a tool that nudges data scientists to improve documentation quality and accountability.

Findings

Significant gap between model card proposals and practice.

DocML effectively encourages better documentation compliance.

Improved documentation quality and accountability with the tool.

Abstract

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.