List your company

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

0.8835AUCMIND
0.240260.4072550.574250.741245Mar 11, 2024

Evaluation results

MethodLinks
MINDBase LLM=OPT-7B2024.030.88350.476
MINDBase LLM=GPT-J-6B2024.030.87740.5244
SCG-NLIBase LLM=GPT-J-6B2024.030.8680.4087
SCG-NLIBase LLM=OPT-7B2024.030.81030.3312
GPT4-HDMBase LLM=OPT-7B2024.030.79720.1678
MINDBase LLM=Falcon-40B2024.030.78950.5032
MINDBase LLM=LLaMA2-Base-7B2024.030.78760.4857
SCG-MQAGBase LLM=GPT-J-6B2024.030.78730.2306
GPT4-HDMBase LLM=GPT-J-6B2024.030.78430.1096
SCG-NLIBase LLM=LLaMA2-Base-7B2024.030.76440.3809
SCG-MQAGBase LLM=OPT-7B2024.030.75930.2151
EUBHDBase LLM=GPT-J-6B2024.030.75930.1057
EUBHDBase LLM=OPT-7B2024.030.75630.1423
SCG-NGBase LLM=GPT-J-6B2024.030.75490.177
EUBHDBase LLM=Falcon-40B2024.030.75090.3161
PE-maxBase LLM=GPT-J-6B2024.030.74970.0839
SCG-NGBase LLM=OPT-7B2024.030.7490.1167
SCG-BSBase LLM=GPT-J-6B2024.030.74240.0745
PP-minBase LLM=GPT-J-6B2024.030.74130.2057
PP-maxBase LLM=OPT-7B2024.030.73020.0732
PE-maxBase LLM=OPT-7B2024.030.72630.0573
PE-minBase LLM=OPT-7B2024.030.72280.0601
LNPPBase LLM=OPT-7B2024.030.72060.2075
PP-minBase LLM=OPT-7B2024.030.71210.1808
PP-maxBase LLM=GPT-J-6B2024.030.7074-0.0467
PE-minBase LLM=GPT-J-6B2024.030.7044-0.0316
LNPEBase LLM=OPT-7B2024.030.70190.1216
SAPLMABase LLM=GPT-J-6B2024.030.69870.0456
LNPEBase LLM=GPT-J-6B2024.030.6980.0376
LNPPBase LLM=GPT-J-6B2024.030.69270.0773
PE-maxBase LLM=LLaMA2-Base-7B2024.030.68510.2032
SCG-NLIBase LLM=Falcon-40B2024.030.68460.3789
MINDBase LLM=LLaMA2-Chat-7B2024.030.67550.4938
SCG-BSBase LLM=OPT-7B2024.030.6594-0.0563
GPT4-HDMBase LLM=LLaMA2-Base-7B2024.030.65830.0086
SCG-NLIBase LLM=LLaMA2-Chat-7B2024.030.65650.3835
PE-maxBase LLM=Falcon-40B2024.030.64790.2405
EUBHDBase LLM=LLaMA2-Base-7B2024.030.64790.117
SCG-BSBase LLM=Falcon-40B2024.030.64180.2293
SCG-MQAGBase LLM=LLaMA2-Base-7B2024.030.64010.1822
GPT4-HDMBase LLM=Falcon-40B2024.030.63290.1346
SAPLMABase LLM=OPT-7B2024.030.6212-0.141
SCG-BSBase LLM=LLaMA2-Base-7B2024.030.61780.1268
LNPEBase LLM=LLaMA2-Base-7B2024.030.61750.1461
LNPPBase LLM=LLaMA2-Base-7B2024.030.60980.1752
MINDBase LLM=LLaMA2-Chat-13B2024.030.60430.4273
PP-minBase LLM=LLaMA2-Base-7B2024.030.60250.1842
PE-minBase LLM=LLaMA2-Base-7B2024.030.58780.0152
PP-maxBase LLM=LLaMA2-Base-7B2024.030.58720.0154
SCG-NLIBase LLM=LLaMA2-Chat-13B2024.030.58340.3092
SAPLMABase LLM=LLaMA2-Base-7B2024.030.5777-0.0015
PE-minBase LLM=Falcon-40B2024.030.57570.1204
PP-maxBase LLM=Falcon-40B2024.030.57490.1193
PP-minBase LLM=Falcon-40B2024.030.55460.1504
LNPEBase LLM=Falcon-40B2024.030.54420.0936
SCG-MQAGBase LLM=Falcon-40B2024.030.54090.0369
SCG-NGBase LLM=LLaMA2-Base-7B2024.030.53650.059
LNPPBase LLM=Falcon-40B2024.030.53270.0667
SCG-NGBase LLM=Falcon-40B2024.030.52180.0995
SAPLMABase LLM=Falcon-40B2024.030.51280.0208
GPT4-HDMBase LLM=LLaMA2-Chat-7B2024.030.51270.1199
PE-maxBase LLM=LLaMA2-Chat-7B2024.030.49310.2029
EUBHDBase LLM=LLaMA2-Chat-7B2024.030.48050.1043
EUBHDBase LLM=LLaMA2-Chat-13B2024.030.46580.2115
SCG-MQAGBase LLM=LLaMA2-Chat-7B2024.030.46130.1856
PP-minBase LLM=LLaMA2-Chat-7B2024.030.44790.1287
PE-maxBase LLM=LLaMA2-Chat-13B2024.030.44390.2375
PE-minBase LLM=LLaMA2-Chat-7B2024.030.44110.0438
PP-maxBase LLM=LLaMA2-Chat-7B2024.030.4166-0.0337
LNPEBase LLM=LLaMA2-Chat-7B2024.030.41140.0858
GPT4-HDMBase LLM=LLaMA2-Chat-13B2024.030.41080.0986
SAPLMABase LLM=LLaMA2-Chat-7B2024.030.40660.013
SCG-MQAGBase LLM=LLaMA2-Chat-13B2024.030.4040.182
SCG-BSBase LLM=LLaMA2-Chat-7B2024.030.376-0.0378
PP-minBase LLM=LLaMA2-Chat-13B2024.030.37250.1092
LNPPBase LLM=LLaMA2-Chat-7B2024.030.3536-0.0339
LNPEBase LLM=LLaMA2-Chat-13B2024.030.33520.0826
PE-minBase LLM=LLaMA2-Chat-13B2024.030.3164-0.0166
SCG-NGBase LLM=LLaMA2-Chat-7B2024.030.3105-0.1016
SAPLMABase LLM=LLaMA2-Chat-13B2024.030.3047-0.0003
SCG-BSBase LLM=LLaMA2-Chat-13B2024.030.3026-0.0136
PP-maxBase LLM=LLaMA2-Chat-13B2024.030.3013-0.0404
LNPPBase LLM=LLaMA2-Chat-13B2024.030.2673-0.0971
SCG-NGBase LLM=LLaMA2-Chat-13B2024.030.265-0.0483