List your company
ResearchFormerly WizWand

Object Hallucination Evaluation on MSCOCO CHAIR

52.4CHAIR_SLLaVA-1.5-7B + Vissink
17.97626.91335.8544.787Jan 28, 2026
Updated 8mo ago

Evaluation results

MethodLinks
LLaVA-1.5-7B + VissinkBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=Vissink2026.0152.414.5
LLaVA-1.5-7BBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=Base2026.014813.9
LLaVA-1.5-7B + ICDBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=ICD2026.0147.713.6
LLaVA-1.5-13BBackbone=LLaVA-1.5, Model Size=13B, Inference Strategy=Base2026.0147.213.6
LLaVA-1.5-7B + VCDBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=VCD2026.0146.813.2
Intern-VL-7BBackbone=Intern-VL, Model Size=7B, Inference Strategy=Base2026.0146.612.4
Intern-VL-13BBackbone=Intern-VL, Model Size=13B, Inference Strategy=Base2026.0145.412.7
LLaVA-1.5-7B + OPERABackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=OPERA2026.0145.212.7
SGRS + LocoREBackbone=Intern-VL, Model Size=13B, Inference Strategy=SGRS + LocoRE2026.0145.214
LLaVA-1.5-7B + SIDBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=SID2026.0144.214
LocoREBackbone=LLaVA-1.5, Model Size=13B, Inference Strategy=LocoRE2026.0143.812.8
LocoREBackbone=Intern-VL, Model Size=13B, Inference Strategy=LocoRE2026.0143.612.5
Qwen2.5-VL-32BBackbone=Qwen2.5-VL, Model Size=32B, Inference Strategy=Base2026.0143.69.5
LocoREBackbone=Qwen2.5-VL, Model Size=32B, Inference Strategy=LocoRE2026.0141.88.5
LLaVA-1.5-7B + FarSightBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=FarSight2026.0141.613.2
LLaVA-1.5-7B + TAMEBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=TAME2026.0141.312.2
LocoREBackbone=Intern-VL, Model Size=7B, Inference Strategy=LocoRE2026.0140.210.5
SGRS + LocoREBackbone=LLaVA-1.5, Model Size=13B, Inference Strategy=SGRS + LocoRE2026.0139.88.8
LocoREBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=LocoRE2026.0138.410.2
SGRS + LocoREBackbone=LLaVA-1.5, Model Size=7B, Inference Strategy=SGRS + LocoRE2026.0135.68.2
SGRS + LocoREBackbone=Intern-VL, Model Size=7B, Inference Strategy=SGRS + LocoRE2026.0134.47.5
Qwen2.5-VL-7BBackbone=Qwen2.5-VL, Model Size=7B, Inference Strategy=Base2026.0127.29
Qwen2-VL-7BBackbone=Qwen2-VL, Model Size=7B, Inference Strategy=Base2026.01257.3
LocoREBackbone=Qwen2-VL, Model Size=7B, Inference Strategy=LocoRE2026.0123.56.8
LocoREBackbone=Qwen2.5-VL, Model Size=7B, Inference Strategy=LocoRE2026.01238.5
SGRS + LocoREBackbone=Qwen2.5-VL, Model Size=7B, Inference Strategy=SGRS + LocoRE2026.01216.5
SGRS + LocoREBackbone=Qwen2-VL, Model Size=7B, Inference Strategy=SGRS + LocoRE2026.0119.35.1