Options Without Agency: Diversity as a Requirement for Fair Actionable Recourse
Peter M. VanNostrand, Dennis M. Hofmann, Lei Ma, and Elke A. Rundensteiner
Published in ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2026
Machine learning systems are increasingly being used to automate life-changing decisions in domains such as finance and recruitment, motivating the development of a myriad of explainable AI techniques. Among them, counterfactual explanations are widely promoted for enabling recourse by suggesting actions that individuals could take to change an unfavorable outcome. Despite their growing adoption, the fairness implications of counterfactual-based recourse remain underexplored. Existing notions of fairness in recourse focus primarily on the number of counterfactuals provided or the magnitude of the changes required to enact each counterfactual to achieve recourse. In this work, we argue that these notions alone are insufficient. Instead, we posit that the diversity of the provided counterfactuals is critical to ensuring that individuals are given meaningful and equitable choices for altering their outcomes. To achieve this, we introduce and analyze a quantitative metric for measuring diversity in recourse on both individual and group levels. Through extensive evaluation across multiple datasets and model architectures, we demonstrate that recourse diversity reliably captures fairness implications not considered by existing fairness metrics and can serve as a valuable signal in guiding model design and selection. This suggests that diversity constitutes an important complementary dimension for assessing fairness in actionable recourse. To facilitate examinations of recourse fairness by the community, we release our auditing tools on GitHub as an open-source framework.
Recommended citation: Peter M. VanNostrand, Dennis M. Hofmann, Lei Ma, and Elke A. Rundensteiner. 2026. Options Without Agency: Diversity as a Requirement for Fair Actionable Recourse. In The 2026 ACM Conference on Fairness, Accountability, and Transparency (FAccT '26), June 25--28, 2026, Montreal, Canada. ACM, New York, NY, USA 19 Pages. https://doi.org/10.1145/3805689.3812337
