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

Object Hallucination Probing on A-OKVQA (Adversarial split)

79.1Accuracy

SchroMind

67.6670.6373.676.57Dec 22, 2025Dec 30, 2025Jan 7, 2026Jan 16, 2026Jan 24, 2026Feb 1, 2026Feb 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
79.180.15
2025.12
79.179.5
2025.12
78.778.9
2025.12
78.779.2
2025.12
78.678.3
2026.02
78.479.71
2025.12
78.479.1
2025.12
7879.9
2025.12
77.579.6
2025.12
75.878.6
2025.12
75.779
2026.02
75.5678.68
2026.02
75.5678.68
2026.02
74.9777.73
2026.02
74.9777.73
2025.12
74.977.6
2025.12
74.977.2
2025.12
74.777.9
2026.02
74.0475.15
2026.02
74.0475.15
2026.02
73.8277.91
2026.02
73.8277.91
2025.12
71.576.4
2025.12
69.175.4
2026.02
68.9775.11
2026.02
68.174.58
2025.12
68.174.9