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

Discriminative Hallucination Evaluation on AMBER-d

89.2Accuracy

Qwen2VL-7B + ACT

68.08873.56979.0584.531Apr 1, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.04
89.2
2026.04
86.6
2026.04
84.8
2026.04
83.4
2026.04
81.8
2026.04
78.9
2026.04
77.8
2026.04
77
2026.04
74
2026.04
71.6
2026.04
71.2
2026.04
68.9