AMNESIA

AMNESIA: A Large-Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis AMNESIA is the first large-scale, open-source benchmark for machine unlearning in the medical domain. It is designed to evaluate methods that selectively remove the influence of specific patient data from trained medical language models while preserving the model's overall clinical knowledge and utility — a capability motivated by privacy regulations such as the GDPR "right to be forgotten."… See the full description on the dataset page: huggingface.co/datasets/dsaeedeh/AMNESIA.