The Limits of Value Transparency in Machine Learning

Abstract

Abstract Transparency has been proposed as a way of handling value-ladenness in machine learning (ML). This article highlights limits to this strategy. I distinguish three kinds of transparency: epistemic transparency, retrospective value transparency, and prospective value transparency. This corresponds to different approaches to transparency in ML, including so-called explainable artificial intelligence and governance based on disclosing information about the design process. I discuss three sources of value-ladenness in ML—problem formulation, inductive risk, and specification gaming—and argue that retrospective value transparency is only well-suited for dealing with the first, while the third raises serious challenges even for prospective value transparency.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.