Selective Prediction

Selective prediction studies how models should decide whether to make a prediction, abstain, or escalate an uncertain case to a person or another system. Common approaches use confidence and uncertainty scores, ensembles or verifiers, and calibration methods such as conformal prediction to set risk–coverage trade-offs. Applications range from image classification and clinical triage to language-model question answering and agent actions, where benchmarks increasingly assess accepted-case errors, coverage, review costs, and subgroup outcomes. A central challenge is that useful confidence rankings do not by themselves guarantee safe decisions: calibration and risk guarantees can depend on data assumptions, shift across domains or groups, and sharply reduce coverage.