Language Model Robustness under Adversarial Attack on MMLU Adversarially Perturbed benchmark leaderboard · SOTA2 Research

Language Model Robustness under Adversarial Attack on MMLU Adversarially Perturbed

43.5AuA (GCG)Adap. RMU

Evaluation Results

Method	Links
Adap. RMU2025.01		43.5	62.4	30.8	75.2	39.2	72.7	50.8	79.2
NPO+MSE2025.01		40.7	57.6	29.1	66.7	40.3	66	46.6	71.2
Base2025.01		40.3	—	33.6	—	39.6	—	52.9	—
RMU2025.01		40.3	60.9	30.5	79.1	38.9	76.4	50.1	84.2
RSV2025.01		39.2	63	30.8	78.2	38.5	75.3	48.7	80.6
Adap. RMU2025.01		38.5	63.5	30.5	80	38.9	76.2	49.8	83.3
RSV2025.01		38.2	62.5	27	77.1	35	73.7	44.2	83.2
SimNPO+MSE2025.01		38.2	58.6	31.5	71.9	42.8	70.1	48.4	75.7
NPO+KL2025.01		35.4	51.2	26.3	61.3	34.7	61.3	43.1	67.7
SimNPO+MSE2025.01		35.4	52.3	29.8	66.7	36.8	66.8	44.5	72.3
NPO+MSE2025.01		34.3	51.6	24.2	66.2	34.3	64.4	46.3	70.9
RMU2025.01		33.6	63	30.5	81.2	38.2	76.8	50.5	85.2
NPO+KL2025.01		31.2	55	25.2	64.1	31.2	62.3	39.2	67
DPO+KL2025.01		30.1	47.3	27.7	58.1	34	57.3	41.7	61.1
SimNPO+KL2025.01		30.1	55	27	61.7	35.4	60.8	44.2	67
DPO+KL2025.01		29.8	56.4	29.1	67	33.3	64.7	42.8	68.9
SimNPO+KL2025.01		29.1	49.9	27	61.1	34.7	60.7	41.7	64.2
DPO+MSE2025.01		28	50.2	19.2	61.1	28.4	61.5	36.8	65.9
DPO+MSE2025.01		27.7	55.6	23.5	57.5	30.5	58.4	39.6	64.3