Our new X account is live! Follow @wizwand_team for updates

Safety Alignment on PKU-SafeRLHF in-distribution (test)

99.44Accuracy (EN)

DPO

Updated 4d ago

Evaluation Results

Method	Links
DPO 2026.02		99.44	98.33	97.22	97.78	96.11	70.56	7.22	50.56	30	17.22	66.44	12.44	0.5437
DPO+MLC 2026.02		99.44	96.67	97.78	98.33	98.33	95	92.78	92.78	91.11	97.22	95.94	0.07	0.9697
DPO+MLC 2026.02		98.33	98.39	96.11	97.22	96.67	95.56	95.56	97.22	95	95	96.83	0.02	0.9989
Raw 2026.02		95.56	95.56	96.11	92.78	97.22	92.22	94.44	93.89	41.11	18.89	81.78	6.97	0.739
DPO 2026.02		95	94.59	93.55	94.62	96.77	91.98	90.91	92.51	48.66	16.58	81.52	6.52	0.7793
Raw 2026.02		93.33	96.11	93.33	92.22	93.89	53.33	6.11	33.89	21.11	12.22	59.55	13.14	0.5037
MPO 2026.02		89.44	81.67	87.78	85.56	87.22	85	76.67	83.33	70.56	42.22	78.95	1.79	0.8942
MPO 2026.02		81.11	81.67	82.22	77.22	78.33	77.22	4.44	70.56	59.44	42.78	65.5	5.53	0.6979
SDRRL 2026.02		57.22	73.33	77.22	75	77.22	72.22	64.44	75.56	69.44	61.11	70.28	0.45	0.8412
SDRRL 2026.02		51.11	78.33	82.22	50.56	73.33	81.67	72.77	80	76.67	72.78	71.94	0.89	0.7288