Mouloud Belbahri — accepted AI-conference papers

2026

Beyond Procedure: Substantive Fairness in Conformal Prediction

Pengqi Liu, Zijun Yu, Mouloud Belbahri, Arthur Charpentier, Masoud Asgharian, Jesse Cresswell

ICML 2026poster

Conformal prediction (CP) offers distribution-free uncertainty quantification for machine learning models, yet its interplay with fairness in downstream decision-making remains underexplored. Moving beyond CP as a standalone operation (procedural fairness), we analyze the holistic decision-making pi…

Cited by 0 Source ↗Scholar ↗

2025

Conformal Prediction Sets Can Cause Disparate Impact

Jesse C. Cresswell, Bhargava Kumar, Yi Sui, Mouloud Belbahri

ICLR 2025spotlight

Conformal prediction is a statistically rigorous method for quantifying uncertainty in models by having them output sets of predictions, with larger sets indicating more uncertainty. However, prediction sets are not inherently actionable; many applications require a single output to act on, not seve…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗