List your company

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

0.9599AUCMIND
0.4566440.5872970.717950.848603Mar 11, 2024

Evaluation results

MethodLinks
MINDBase LLM=GPT-J-6B2024.030.95990.5296
MINDBase LLM=OPT-7B2024.030.94490.5636
SCG-NLIBase LLM=GPT-J-6B2024.030.93840.4217
GPT4-HDMBase LLM=OPT-7B2024.030.91960.2372
GPT4-HDMBase LLM=GPT-J-6B2024.030.91830.2539
SCG-NLIBase LLM=OPT-7B2024.030.90960.4091
MINDBase LLM=LLaMA2-Base-7B2024.030.90480.4911
SCG-NLIBase LLM=LLaMA2-Base-7B2024.030.88970.4389
MINDBase LLM=Falcon-40B2024.030.88860.5251
PE-maxBase LLM=GPT-J-6B2024.030.88750.266
PE-maxBase LLM=OPT-7B2024.030.88510.218
SCG-MQAGBase LLM=GPT-J-6B2024.030.88270.3145
EUBHDBase LLM=Falcon-40B2024.030.86590.3447
GPT4-HDMBase LLM=LLaMA2-Base-7B2024.030.86250.1876
SCG-MQAGBase LLM=OPT-7B2024.030.85940.2993
SCG-NGBase LLM=GPT-J-6B2024.030.85790.2222
EUBHDBase LLM=GPT-J-6B2024.030.8560.1546
MINDBase LLM=LLaMA2-Chat-7B2024.030.85470.4778
EUBHDBase LLM=OPT-7B2024.030.85450.1342
PP-minBase LLM=GPT-J-6B2024.030.85260.2454
PE-maxBase LLM=LLaMA2-Base-7B2024.030.840.2561
PP-minBase LLM=OPT-7B2024.030.83840.1191
LNPPBase LLM=OPT-7B2024.030.83740.2417
LNPEBase LLM=OPT-7B2024.030.83490.1879
PE-maxBase LLM=Falcon-40B2024.030.83470.3106
SCG-NGBase LLM=OPT-7B2024.030.8340.1021
SAPLMABase LLM=GPT-J-6B2024.030.82940.1298
SCG-MQAGBase LLM=LLaMA2-Base-7B2024.030.81960.2278
SCG-BSBase LLM=GPT-J-6B2024.030.81650.1288
GPT4-HDMBase LLM=Falcon-40B2024.030.8150.0812
SCG-NLIBase LLM=Falcon-40B2024.030.81210.4062
LNPEBase LLM=GPT-J-6B2024.030.81110.1261
PP-maxBase LLM=OPT-7B2024.030.810.0943
PE-minBase LLM=OPT-7B2024.030.80750.0832
LNPPBase LLM=GPT-J-6B2024.030.80390.1601
PP-minBase LLM=LLaMA2-Base-7B2024.030.79690.2231
SCG-NLIBase LLM=LLaMA2-Chat-7B2024.030.79510.4005
EUBHDBase LLM=LLaMA2-Base-7B2024.030.78590.1693
SAPLMABase LLM=LLaMA2-Base-7B2024.030.78230.0271
LNPEBase LLM=LLaMA2-Base-7B2024.030.77760.2018
GPT4-HDMBase LLM=LLaMA2-Chat-7B2024.030.77680.1883
LNPPBase LLM=LLaMA2-Base-7B2024.030.77550.2297
PP-minBase LLM=Falcon-40B2024.030.76490.1815
SCG-BSBase LLM=LLaMA2-Base-7B2024.030.76310.1447
SCG-BSBase LLM=OPT-7B2024.030.7597-0.0732
PE-minBase LLM=GPT-J-6B2024.030.7595-0.0645
PE-minBase LLM=LLaMA2-Base-7B2024.030.75870.0928
PP-maxBase LLM=GPT-J-6B2024.030.7585-0.0672
SCG-NLIBase LLM=LLaMA2-Chat-13B2024.030.75590.4145
PP-maxBase LLM=LLaMA2-Base-7B2024.030.75430.0837
SAPLMABase LLM=OPT-7B2024.030.7476-0.1433
SCG-BSBase LLM=Falcon-40B2024.030.74280.2471
SCG-MQAGBase LLM=LLaMA2-Chat-7B2024.030.72840.2581
SCG-MQAGBase LLM=Falcon-40B2024.030.7275-0.0851
SAPLMABase LLM=Falcon-40B2024.030.72360.09
MINDBase LLM=LLaMA2-Chat-13B2024.030.71750.3823
SCG-NGBase LLM=LLaMA2-Base-7B2024.030.71550.0785
LNPEBase LLM=Falcon-40B2024.030.71450.102
EUBHDBase LLM=LLaMA2-Chat-7B2024.030.71260.0512
SCG-NGBase LLM=Falcon-40B2024.030.71240.0575
PE-minBase LLM=Falcon-40B2024.030.71150.0855
PP-maxBase LLM=Falcon-40B2024.030.70630.0843
LNPPBase LLM=Falcon-40B2024.030.70080.0706
PE-maxBase LLM=LLaMA2-Chat-7B2024.030.69880.1956
PP-minBase LLM=LLaMA2-Chat-7B2024.030.6870.1668
LNPEBase LLM=LLaMA2-Chat-7B2024.030.67040.2258
EUBHDBase LLM=LLaMA2-Chat-13B2024.030.66850.3079
SCG-MQAGBase LLM=LLaMA2-Chat-13B2024.030.66720.2902
PP-maxBase LLM=LLaMA2-Chat-7B2024.030.66140.1426
PE-minBase LLM=LLaMA2-Chat-7B2024.030.64090.2382
SAPLMABase LLM=LLaMA2-Chat-7B2024.030.62650.0519
LNPPBase LLM=LLaMA2-Chat-7B2024.030.59520.1169
SCG-BSBase LLM=LLaMA2-Chat-7B2024.030.5938-0.0504
PE-maxBase LLM=LLaMA2-Chat-13B2024.030.59330.2258
PE-minBase LLM=LLaMA2-Chat-13B2024.030.59180.0826
GPT4-HDMBase LLM=LLaMA2-Chat-13B2024.030.590.053
LNPEBase LLM=LLaMA2-Chat-13B2024.030.58780.2867
SCG-NGBase LLM=LLaMA2-Chat-7B2024.030.5771-0.1348
LNPPBase LLM=LLaMA2-Chat-13B2024.030.55220.2188
PP-maxBase LLM=LLaMA2-Chat-13B2024.030.5344-0.0426
PP-minBase LLM=LLaMA2-Chat-13B2024.030.53010.094
SAPLMABase LLM=LLaMA2-Chat-13B2024.030.5179-0.0714
SCG-NGBase LLM=LLaMA2-Chat-13B2024.030.4983-0.1065
SCG-BSBase LLM=LLaMA2-Chat-13B2024.030.476-0.0138