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

Medical Subject Classification (Healthcare) on PubMed Synthetic GPT-2-large generated (test)

74.96Accuracy

Federated GPT-2-large

52.787258.543664.370.0564Mar 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
74.9674.98
2026.03
74.3674.42
2026.03
74.3274.38
2026.03
7474.06
2026.03
73.6873.26
2026.03
73.6873.74
2026.03
73.4873.41
2026.03
71.6471.59
2026.03
71.471.44
2026.03
69.9669.96
2026.03
63.8462.93
2026.03
62.8461.87
2026.03
62.261.79
2026.03
60.7660.86
2026.03
59.0858.54
2026.03
58.6456.96
2026.03
53.6451.79