Machine Unlearning on MedMCQA QF=1000 benchmark leaderboard · SOTA2 Research

Machine Unlearning on MedMCQA QF=1000

90Forget AccuracySequential Retrain

Evaluation Results

Method	Links
Sequential Retrain2026.02		90	88	88.67	0.509	0.982
Sequential Retrain2026.02		90	88	88.67	0.509	0.982
Origin2026.02		89	88	90	0.549	0.902
Origin2026.02		89	88	90	0.549	0.902
Adapter Merging2026.02		88.67	88.67	85.33	0.5087	0.9827
Adapter Merging2026.02		88.67	88.67	85.33	0.5087	0.9827
GA2026.02		87.33	88.67	87.67	0.508	0.984
GA2026.02		87.33	88.67	87.67	0.508	0.984
NPO2026.02		86	87	83	0.509	0.982
NPO2026.02		86	87	83	0.509	0.982
Sequential LoRA2026.02		76.67	87.67	89	0.508	0.984
Sequential LoRA2026.02		76.67	87.67	89	0.508	0.984
SBU2026.02		71.33	89.33	89	0.5	0.996
SBU2026.02		71.33	89.33	89	0.5	0.996