Share your thoughts, 1 month free Claude Pro on usSee more

Model Editing on FEVER

98.23Efficacy

UltraEdit*

Updated 1mo ago

Evaluation Results

Method	Links
UltraEdit* 2025.05		98.23	96.97	83.43
UltraEdit* 2025.05		98.23	96.97	83.43
UltraEdit 2025.05		97.97	93.91	68.86
UltraEdit* 2025.05		97.89	96.73	79.85
UltraEdit* 2025.05		97.89	96.73	79.85
UltraEdit 2025.05		97.87	96.09	84.29
UltraEdit 2025.05		97.87	96.09	84.29
UltraEdit* 2025.05		97.49	94.83	68.99
UltraEdit 2025.05		97.45	96.37	79.72
UltraEdit 2025.05		97.45	96.37	79.72
UltraEdit* 2025.05		97.18	94.64	68.62
UltraEdit* 2025.05		97.18	94.64	68.62
UltraEdit 2025.05		95.39	91.93	67.14
UltraEdit 2025.05		95.39	91.93	67.14
MALMEN 2025.05		94.5	91.26	67.76
RLEdit 2025.05		94.03	90.67	68.71
WISE 2025.05		93.95	92.86	57.03
RLEdit 2025.05		92.35	91.39	71.85
WISE 2025.05		86.38	86.36	72.08
WISE 2025.05		81.95	76.94	40.37
MEND 2025.05		76.43	77.66	40.39
MEND 2025.05		52.8	51.44	45.42
MEND 2025.05		36.19	36.19	24.31
AlphaEdit 2025.05		32.78	31.19	22.12
FT 2025.05		26.09	24.62	21.36
FT 2025.05		23.8	23.37	16.3
MALMEN 2025.05		18.42	17.43	12.09
RECT 2025.05		18.12	18.08	12.27
FT 2025.05		16.21	13.08	5.01
RLEdit 2025.05		14.26	13.74	14.11
FT 2025.05		14.02	13.98	9.26
AlphaEdit 2025.05		6.39	6.14	2.72
MEMIT 2025.05		5.54	5.03	5.46
PRUNE 2025.05		5.25	4.72	5.2
RECT 2025.05		3.36	3.1	3.2
AlphaEdit 2025.05		1.89	1.87	1.85
MALMEN 2025.05		1.33	1.25	2.92
MEMIT 2025.05		0.08	0.12	0.15
PRUNE 2025.05		0.08	0.15	0.11
MALMEN 2025.05		0.06	0.06	0.07
MEMIT 2025.05		0.02	0.02	0.02
PRUNE 2025.05		0.02	0.02	0
RECT 2025.05		0.01	0	0
AlphaEdit 2025.05		0	0	0
RLEdit 2025.05		0	0	0
MEND 2025.05		0	0	0
MEMIT 2025.05		0	0	0
RECT 2025.05		0	0	0
PRUNE 2025.05		0	0	0