REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research

TL;DR

This paper introduces REAL ML, a set of guided activities designed to help machine learning researchers recognize, explore, and articulate research limitations to improve transparency and scientific rigor.

Contribution

The paper presents the development and testing of REAL ML, a novel framework to assist ML researchers in systematically addressing limitations in their work.

Findings

Researchers perceive limitations as important but face practical challenges in articulating them.

REAL ML effectively guides researchers in recognizing and exploring research limitations.

Addressing cultural norms is necessary for broader acceptance of limitation disclosure.

Abstract

Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible. Despite these benefits, the machine learning (ML) research community lacks well-developed norms around disclosing and discussing limitations. To address this gap, we conduct an iterative design process with 30 ML and ML-adjacent researchers to develop and test REAL ML, a set of guided activities to help ML researchers recognize, explore, and articulate the limitations of their research. Using a three-stage interview and survey study, we identify ML researchers' perceptions of limitations, as well as the challenges they face when recognizing, exploring, and articulating limitations. We develop REAL ML to address some of these practical challenges, and highlight additional cultural challenges that will require broader shifts in community norms to address. We hope our study and REAL ML help move the ML research community toward more active and appropriate engagement with limitations.