Reflexive Design for Fairness and Other Human Values in Formal Models

Algorithms and other formal models that incorporate human values like fairness have grown increasingly popular in computer science. In response to sociotechnical challenges in the use of these models, designers and researchers have taken widely divergent positions on the use of formal models of human values: encouraging their use, moving away from them, or ignoring the normative consequences altogether. In this paper, we seek to resolve these divergent positions by identifying the main conceptual limits of formal modeling, and develop four reflexive values-value fidelity, accuracy, value legibility, and value contestation-vital for incorporating human values into formal models. We then provide a methodology for reflexively designing formal models incorporating human values without ignoring their societal implications.