A New Paradigm for Counterfactual Reasoning in Fairness and Recourse

A New Paradigm for Counterfactual Reasoning in Fairness and Recourse

Lucius E.J. Bynum, Joshua R. Loftus, Julia Stoyanovich

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 7092-7100. https://doi.org/10.24963/ijcai.2024/784

Counterfactuals underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is the interventional counterfactual, where hypothetical interventions are imagined and simulated. For this reason, the starting point for causal reasoning about legal protections and demographic data in AI is an imagined intervention on a legally-protected characteristic, such as ethnicity, race, gender, disability, age, etc. We ask, for example, what would have happened had your race been different? An inherent limitation of this paradigm is that some demographic interventions — like interventions on race — may not be well-defined or translate into the formalisms of interventional counterfactuals. In this work, we explore a new paradigm based instead on the backtracking counterfactual, where rather than imagine hypothetical interventions on legally-protected characteristics, we imagine alternate initial conditions while holding these characteristics fixed. We ask instead, what would explain a counterfactual outcome for you as you actually are or could be? This alternate framework allows us to address many of the same social concerns, but to do so while asking fundamentally different questions that do not rely on demographic interventions.
Keywords:
Uncertainty in AI: UAI: Causality, structural causal models and causal inference
AI Ethics, Trust, Fairness: ETF: Fairness and diversity
AI Ethics, Trust, Fairness: ETF: Moral decision making
Machine Learning: ML: Causality