Medical Subject Classification (Healthcare) on PubMed Synthetic GPT-2-large generated (test)
74.96AccuracyFederated GPT-2-large
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Federated GPT-2-largeCs%=40%, epsilon=∞, refinement=false2026.03 | 74.96 | 74.98 | |
| Federated GPT-2-largeCs%=40%, epsilon=8, refinement=true2026.03 | 74.36 | 74.42 | |
| Federated GPT-2-largeCs%=30%, epsilon=∞, refinement=false2026.03 | 74.32 | 74.38 | |
| Federated GPT-2-largeCs%=30%, epsilon=8, refinement=true2026.03 | 74 | 74.06 | |
| Federated GPT-2-largeCs%=5%, epsilon=8, refinement=true2026.03 | 73.68 | 73.26 | |
| Federated GPT-2-largeCs%=20%, epsilon=8, refinement=true2026.03 | 73.68 | 73.74 | |
| Federated GPT-2-largeCs%=10%, epsilon=8, refinement=true2026.03 | 73.48 | 73.41 | |
| Federated GPT-2-largeCs%=10%, epsilon=∞, refinement=false2026.03 | 71.64 | 71.59 | |
| Federated GPT-2-largeCs%=20%, epsilon=∞, refinement=false2026.03 | 71.4 | 71.44 | |
| Federated GPT-2-largeCs%=5%, epsilon=∞, refinement=false2026.03 | 69.96 | 69.96 | |
| Federated GPT-2-largeCs%=40%, epsilon=8, refinement=false2026.03 | 63.84 | 62.93 | |
| Federated GPT-2-largeCs%=30%, epsilon=8, refinement=false2026.03 | 62.84 | 61.87 | |
| Federated GPT-2-largeCs%=20%, epsilon=8, refinement=false2026.03 | 62.2 | 61.79 | |
| Federated GPT-2-largeCs%=10%, epsilon=8, refinement=false2026.03 | 60.76 | 60.86 | |
| Federated GPT-2-largeCs%=5%, epsilon=8, refinement=false2026.03 | 59.08 | 58.54 | |
| GPT-2-large (Pretrained)Cs%=Pre., epsilon=8, refinement=true2026.03 | 58.64 | 56.96 | |
| GPT-2-large (Pretrained)Cs%=Pre., epsilon=∞, refinement=false2026.03 | 53.64 | 51.79 |