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

Hallucination Detection on HELM Passage Level v1.0 (test)

0.9599AUC

MIND

0.4566440.5872970.717950.848603Mar 11, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.03
0.95990.5296
2024.03
0.94490.5636
2024.03
0.93840.4217
2024.03
0.91960.2372
2024.03
0.91830.2539
2024.03
0.90960.4091
2024.03
0.90480.4911
2024.03
0.88970.4389
2024.03
0.88860.5251
2024.03
0.88750.266
2024.03
0.88510.218
2024.03
0.88270.3145
2024.03
0.86590.3447
2024.03
0.86250.1876
2024.03
0.85940.2993
2024.03
0.85790.2222
2024.03
0.8560.1546
2024.03
0.85470.4778
2024.03
0.85450.1342
2024.03
0.85260.2454
2024.03
0.840.2561
2024.03
0.83840.1191
2024.03
0.83740.2417
2024.03
0.83490.1879
2024.03
0.83470.3106
2024.03
0.8340.1021
2024.03
0.82940.1298
2024.03
0.81960.2278
2024.03
0.81650.1288
2024.03
0.8150.0812
2024.03
0.81210.4062
2024.03
0.81110.1261
2024.03
0.810.0943
2024.03
0.80750.0832
2024.03
0.80390.1601
2024.03
0.79690.2231
2024.03
0.79510.4005
2024.03
0.78590.1693
2024.03
0.78230.0271
2024.03
0.77760.2018
2024.03
0.77680.1883
2024.03
0.77550.2297
2024.03
0.76490.1815
2024.03
0.76310.1447
2024.03
0.7597-0.0732
2024.03
0.7595-0.0645
2024.03
0.75870.0928
2024.03
0.7585-0.0672
2024.03
0.75590.4145
2024.03
0.75430.0837
2024.03
0.7476-0.1433
2024.03
0.74280.2471
2024.03
0.72840.2581
2024.03
0.7275-0.0851
2024.03
0.72360.09
2024.03
0.71750.3823
2024.03
0.71550.0785
2024.03
0.71450.102
2024.03
0.71260.0512
2024.03
0.71240.0575
2024.03
0.71150.0855
2024.03
0.70630.0843
2024.03
0.70080.0706
2024.03
0.69880.1956
2024.03
0.6870.1668
2024.03
0.67040.2258
2024.03
0.66850.3079
2024.03
0.66720.2902
2024.03
0.66140.1426
2024.03
0.64090.2382
2024.03
0.62650.0519
2024.03
0.59520.1169
2024.03
0.5938-0.0504
2024.03
0.59330.2258
2024.03
0.59180.0826
2024.03
0.590.053
2024.03
0.58780.2867
2024.03
0.5771-0.1348
2024.03
0.55220.2188
2024.03
0.5344-0.0426
2024.03
0.53010.094
2024.03
0.5179-0.0714
2024.03
0.4983-0.1065
2024.03
0.476-0.0138