List your company

Open-ended Hallucination Evaluation on Open-ended hallucination benchmark

1.46ScoreREC
0.79440.96721.141.3128Jun 7, 2026

Evaluation results

MethodLinks
RECModel=Qwen2.5-3B2026.061.464.22
PoDModel=Qwen2.5-3B2026.061.444.21
BaseModel=Qwen2.5-3B2026.061.44.19
RECModel=LLaMA3-3B2026.061.45.32
PoDModel=LLaMA3-3B2026.061.385.31
PoEModel=Qwen2.5-3B2026.061.384.24
BaseModel=LLaMA3-3B2026.061.345.33
PoEModel=LLaMA3-3B2026.061.325.28
RECModel=Qwen2.5-7B2026.061.323.26
PoDModel=Qwen2.5-7B2026.061.33.25
BaseModel=Qwen2.5-7B2026.061.283.23
CAAModel=Qwen2.5-3B2026.061.284.32
PoEModel=Qwen2.5-7B2026.061.263.28
HPRModel=Qwen2.5-3B2026.061.264.35
RECModel=LLaMA3-8B2026.061.262.99
CAAModel=LLaMA3-3B2026.061.245.2
PoDModel=LLaMA3-8B2026.061.242.95
BaseModel=LLaMA3-8B2026.061.222.94
HPRModel=LLaMA3-3B2026.061.225.4
INNSTEERModel=Qwen2.5-3B2026.061.224.31
PoEModel=LLaMA3-8B2026.061.22.97
ITIModel=Qwen2.5-3B2026.061.24.38
CAAModel=Qwen2.5-7B2026.061.183.51
LAcTModel=Qwen2.5-3B2026.061.184.37
INNSTEERModel=LLaMA3-3B2026.061.185.16
ITIModel=LLaMA3-3B2026.061.165.45
HPRModel=Qwen2.5-7B2026.061.163.49
ODEModel=Qwen2.5-3B2026.061.164.4
LAcTModel=LLaMA3-3B2026.061.145.44
TFModel=Qwen2.5-3B2026.061.144.42
CAAModel=LLaMA3-8B2026.061.123
ODEModel=LLaMA3-3B2026.061.125.46
ITIModel=Qwen2.5-7B2026.061.13.55
HPRModel=LLaMA3-8B2026.061.13.03
TFModel=LLaMA3-3B2026.061.15.48
RECModel=Qwen2.5-32B2026.061.082.91
LAcTModel=Qwen2.5-7B2026.061.083.53
PoDModel=Qwen2.5-32B2026.061.062.91
ODEModel=Qwen2.5-7B2026.061.063.57
BaseModel=Qwen2.5-32B2026.061.042.9
ITIModel=LLaMA3-8B2026.061.043.05
TFModel=Qwen2.5-7B2026.061.043.6
PoEModel=Qwen2.5-32B2026.061.022.92
LAcTModel=LLaMA3-8B2026.061.023.04
ODEModel=LLaMA3-8B2026.0613.06
CAAModel=Qwen2.5-32B2026.060.982.96
TFModel=LLaMA3-8B2026.060.983.07
INNSTEERModel=Qwen2.5-7B2026.060.983.45
HPRModel=Qwen2.5-32B2026.060.962.98
INNSTEERModel=LLaMA3-8B2026.060.942.98
ITIModel=Qwen2.5-32B2026.060.923
LAcTModel=Qwen2.5-32B2026.060.92.99
ODEModel=Qwen2.5-32B2026.060.883.01
TFModel=Qwen2.5-32B2026.060.863.03
INNSTEERModel=Qwen2.5-32B2026.060.822.88