Algorithmic Fairness

The field asks whether automated systems treat people and groups fairly, using criteria such as demographic parity, equalized odds, individual similarity, and causal or counterfactual fairness. Researchers audit disparities in credit, hiring, healthcare, recommendation, and language or vision models, using benchmarks such as COMPAS, Adult, and MIMIC alongside subgroup and intersectional tests. Mitigation ranges from data reweighting and representation learning to constrained or robust optimization, causal interventions, and post-hoc thresholding; work also studies fairness in rankings, sequential allocation, federated learning, and LLM agents. A central challenge is that fairness criteria can conflict with one another and with utility, while estimates and interventions may be unstable under small samples, distribution shift, strategic behavior, or uncertain causal assumptions.