List your company

Hallucination Evaluation on CHAIR MSCOCO

59.4CHAIR_SVCD
11.0423.59536.1548.705Mar 25, 2026

Evaluation results

MethodLinks
VCDBase Model=LLaVA-1.5, Max New Tokens=2562026.0359.416
DoLABase Model=Shikra, Max New Tokens=2562026.0355.714.8
GreedyBase Model=Shikra, Max New Tokens=2562026.0355.415.2
VCDBase Model=Shikra, Max New Tokens=2562026.0354.915.1
GreedyBase Model=InstructBLIP, Max New Tokens=2562026.0354.720.2
DoLABase Model=LLaVA-1.5, Max New Tokens=2562026.035414.2
DoLABase Model=InstructBLIP, Max New Tokens=2562026.0352.819.1
GreedyBase Model=LLaVA-1.5, Max New Tokens=2562026.0351.813.7
FarSightBase Model=Shikra, Max New Tokens=2562026.0351.612.2
HALCBase Model=LLaVA-1.5, Max New Tokens=2562026.0351.413.1
VCDBase Model=InstructBLIP, Max New Tokens=2562026.0350.119.4
FarSightBase Model=InstructBLIP, Max New Tokens=2562026.0348.318.7
OPERABase Model=InstructBLIP, Max New Tokens=2562026.0348.214.3
HALCBase Model=InstructBLIP, Max New Tokens=2562026.034815.3
HALCBase Model=Shikra, Max New Tokens=2562026.0347.214.5
OPERABase Model=LLaVA-1.5, Max New Tokens=2562026.0344.112.8
FarSightBase Model=LLaVA-1.5, Max New Tokens=2562026.0343.912.5
GreedyBase Model=MiniGPT4, Max New Tokens=2562026.034313.4
DoLABase Model=MiniGPT4, Max New Tokens=2562026.034213.5
VCDBase Model=MiniGPT4, Max New Tokens=2562026.034014.6
FarSightBase Model=MiniGPT4, Max New Tokens=2562026.0339.212.4
OPERABase Model=Shikra, Max New Tokens=2562026.0338.214.2
HALCBase Model=MiniGPT4, Max New Tokens=2562026.0337.412.1
OPERABase Model=MiniGPT4, Max New Tokens=2562026.0337.313.5
AD-HHBase Model=Shikra, Max New Tokens=2562026.0336.913.7
AD-HHBase Model=InstructBLIP, Max New Tokens=2562026.033610.3
AD-HHBase Model=LLaVA-1.5, Max New Tokens=2562026.0335.28.8
VCDBase Model=InstructBLIP, Max New Tokens=642026.0334.115.8
AD-HHBase Model=MiniGPT4, Max New Tokens=2562026.0332.811.5
AIRBase Model=Shikra, Max New Tokens=2562026.0330.39.3
AIRBase Model=InstructBLIP, Max New Tokens=2562026.0330.18.6
GreedyBase Model=InstructBLIP, Max New Tokens=642026.0329.814.2
GreedyBase Model=MiniGPT4, Max New Tokens=642026.0328.811.4
AIRBase Model=LLaVA-1.5, Max New Tokens=2562026.0328.88.6
DoLABase Model=MiniGPT4, Max New Tokens=642026.0328.611.5
DoLABase Model=InstructBLIP, Max New Tokens=642026.0328.114.2
VCDBase Model=MiniGPT4, Max New Tokens=642026.032811.3
OPERABase Model=MiniGPT4, Max New Tokens=642026.0326.610.4
HALCBase Model=MiniGPT4, Max New Tokens=642026.0324.29.7
HALCBase Model=InstructBLIP, Max New Tokens=642026.0324.214.1
VCDBase Model=Shikra, Max New Tokens=642026.0323.58.3
VCDBase Model=LLaVA-1.5, Max New Tokens=642026.0322.87.1
FarSightBase Model=MiniGPT4, Max New Tokens=642026.0322.58.9
GreedyBase Model=Shikra, Max New Tokens=642026.0322.38.2
DoLABase Model=LLaVA-1.5, Max New Tokens=642026.0322.26.7
AD-HHBase Model=MiniGPT4, Max New Tokens=642026.03228.5
AIRBase Model=MiniGPT4, Max New Tokens=2562026.0321.38.9
HALCBase Model=LLaVA-1.5, Max New Tokens=642026.0321.26.6
GreedyBase Model=LLaVA-1.5, Max New Tokens=642026.0320.86.2
FarSightBase Model=InstructBLIP, Max New Tokens=642026.0320.29.6
DoLABase Model=Shikra, Max New Tokens=642026.0320.29.6
AD-HHBase Model=InstructBLIP, Max New Tokens=642026.0319.68.5
FarSightBase Model=LLaVA-1.5, Max New Tokens=642026.0318.65.9
OPERABase Model=InstructBLIP, Max New Tokens=642026.0318.48.7
OPERABase Model=LLaVA-1.5, Max New Tokens=642026.0317.86.5
AIRBase Model=MiniGPT4, Max New Tokens=642026.0317.27.5
AIRBase Model=InstructBLIP, Max New Tokens=642026.0316.38.1
AD-HHBase Model=LLaVA-1.5, Max New Tokens=642026.0315.65.7
FarSightBase Model=Shikra, Max New Tokens=642026.0315.47.6
AIRBase Model=LLaVA-1.5, Max New Tokens=642026.0314.85.1
OPERABase Model=Shikra, Max New Tokens=642026.0314.67.4
HALCBase Model=Shikra, Max New Tokens=642026.0314.47.8
AD-HHBase Model=Shikra, Max New Tokens=642026.0313.87
AIRBase Model=Shikra, Max New Tokens=642026.0312.97