Perspectives on Incorporating Expert Feedback into Model Updates

TL;DR

This paper proposes a systematic taxonomy for integrating non-technical expert feedback into machine learning model updates, addressing a gap in how domain expertise influences model development.

Contribution

It introduces a feedback-update taxonomy that categorizes expert feedback types and their corresponding model update methods, bridging ML and human-computer interaction perspectives.

Findings

Taxonomy matches feedback types with update methods

Highlights gaps in incorporating non-technical expert input

Provides open questions for future research

Abstract

Machine learning (ML) practitioners are increasingly tasked with developing models that are aligned with non-technical experts' values and goals. However, there has been insufficient consideration on how practitioners should translate domain expertise into ML updates. In this paper, we consider how to capture interactions between practitioners and experts systematically. We devise a taxonomy to match expert feedback types with practitioner updates. A practitioner may receive feedback from an expert at the observation- or domain-level, and convert this feedback into updates to the dataset, loss function, or parameter space. We review existing work from ML and human-computer interaction to describe this feedback-update taxonomy, and highlight the insufficient consideration given to incorporating feedback from non-technical experts. We end with a set of open questions that naturally arise from our proposed taxonomy and subsequent survey.