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

Object Hallucination Detection on MME existence

98.33Accuracy

R-CoV

Updated 1mo ago

Evaluation Results

Method	Links
R-CoV 2026.04		98.33	96.67
R-CoV 2026.04		98.33	96.67
R-CoV 2026.04		96.67	93.33
Vanilla 2026.04		96.67	93.33
SelfCheck 2026.04		96.67	93.33
LogicCheckGPT 2026.04		96.67	93.33
LogicCheckGPT 2026.04		95	90
Vanilla 2026.04		95	90
LogicCheckGPT 2026.04		95	90
LURE 2026.04		93.33	86.67
R-CoV 2026.04		88.33	76.67
LogicCheckGPT 2026.04		86.67	73.33
SelfCheck 2026.04		85	73.33
LURE 2026.04		85	70
LRV-Instruction 2026.04		83.33	66.67
LRV-Instruction 2026.04		83.33	66.67
LURE 2026.04		80	60
SelfCheck 2026.04		80	60
Vanilla 2026.04		78.33	56.67
Vanilla 2026.04		65	35