DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas
arXiv:2610.38431v1 Announce Type: cross Abstract: Machine unlearning aims to reproduce the behavior of a model trained without designated data. For probabilistic decision models, this target also depends on the candidate options supplied at inference. We introduce DecisionUnlearn-Bench, an empirical framework that compares full, unlearned, and retain-only models across deletion granularities, label renderings, and candidate sets. Across 20 eligible model configurations on the BANKING77 dataset,…