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

Discriminative Hallucination Evaluation on AMBER (Acc, P, R, F1)

84.3Accuracy

MESA

66.30870.97975.6580.321Apr 4, 2026Apr 6, 2026Apr 9, 2026Apr 12, 2026Apr 14, 2026Apr 17, 2026Apr 20, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
84.390.385.487.8
2026.04
81.587.484.285.8
2026.04
81.2--85
2026.04
79.584.784.484.5
2026.04
79.182.187.684.8
2026.04
76.7--82.7
2026.04
74.173.296.283.1
2026.04
73.983.875.279.3
2026.04
73.585.772.878.7
2026.04
73.385.174.279.3
2026.04
71.481.973.177.2
2026.04
71.189.563.974.6
2026.04
70.7--75.5
2026.04
709061.773.2
2026.04
69.894.857.671.7
2026.04
67.3--71.1
2026.04
67.3--70.9
67--71.1