Medical Long-form Generation on MedB-4 (test)
76SM ScoreAPCD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| APCDBackbone=II-Medical-8B-1706, Decoding Strategy=APCD2026.05 | 76 | 78.3 | |
| CSBackbone=II-Medical-8B-1706, Decoding Strategy=CS2026.05 | 75.2 | 78.1 | |
| Sample (top k + top p)Backbone=II-Medical-8B-1706, Decoding Strategy=Sample (top k + top p)2026.05 | 70.8 | 77.6 | |
| DoLa (low)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (low)2026.05 | 70.1 | 74 | |
| II-Medical-8B-1706Backbone=II-Medical-8B-1706, Decoding Strategy=Standard2026.05 | 68.4 | 75.6 | |
| Beam SearchBackbone=II-Medical-8B-1706, Decoding Strategy=Beam Search2026.05 | 67.2 | 72.7 | |
| DBSBackbone=II-Medical-8B-1706, Decoding Strategy=DBS2026.05 | 62 | 75 | |
| DoLa (high)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (high)2026.05 | 8.1 | 8.1 |