Medical Long-form Generation on NEJM (test)
76.6SM ScoreAPCD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| APCDBackbone=II-Medical-8B-1706, Decoding Strategy=APCD2026.05 | 76.6 | 78 | |
| CSBackbone=II-Medical-8B-1706, Decoding Strategy=CS2026.05 | 72.5 | 75.3 | |
| DoLa (low)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (low)2026.05 | 70.3 | 73.1 | |
| II-Medical-8B-1706Backbone=II-Medical-8B-1706, Decoding Strategy=Standard2026.05 | 67.7 | 71.5 | |
| Sample (top k + top p)Backbone=II-Medical-8B-1706, Decoding Strategy=Sample (top k + top p)2026.05 | 67.2 | 73.6 | |
| Beam SearchBackbone=II-Medical-8B-1706, Decoding Strategy=Beam Search2026.05 | 67.2 | 73.2 | |
| DBSBackbone=II-Medical-8B-1706, Decoding Strategy=DBS2026.05 | 65.1 | 72 | |
| DoLa (high)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (high)2026.05 | 11.2 | 11.5 |