Perspectives on Incorporating Expert Feedback into Model Updates
This work addresses the challenge for ML practitioners in aligning models with expert values, though it is incremental as it primarily reviews and organizes existing concepts.
The paper tackles the problem of systematically incorporating non-technical expert feedback into machine learning model updates by proposing a taxonomy that matches feedback types with update methods, but does not present experimental results or concrete numbers.
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.