Medical Knowledge Evaluation on Medbullets
58.44AccuracyHPS-CPT
Evaluation Results
| Method | Links | |
|---|---|---|
| HPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=High-PPL Sampling2025.12 | 58.44 | |
| DOS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Distance-to-Optimum Selection2025.12 | 57.14 | |
| RS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Random Data Sampling2025.12 | 56.82 | |
| LPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Low-PPL Sampling2025.12 | 56.82 | |
| Qwen3-14B-BaseBackbone=Qwen3-14B-Base, CPT Strategy=None2025.12 | 55.52 |