Question Answering on MedMCQA (R@1, R@3, N@1, N@3)
72.33R@1S-DPO
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| S-DPOModel=Llama32026.05 | 72.33 | 94.34 | 72.33 | 85.2 | |
| MASS-DPOModel=Llama32026.05 | 71.23 | 94.49 | 71.23 | 84.84 | |
| DPO-kModel=Llama32026.05 | 71.13 | 93.88 | 71.13 | 84.51 | |
| MASS-DPOModel=Qwen32026.05 | 56.34 | 89.72 | 56.34 | 75.62 | |
| DPO-kModel=Qwen32026.05 | 54.59 | 89.67 | 54.59 | 74.86 | |
| DPOModel=Llama32026.05 | 51.48 | 87.82 | 51.48 | 72.3 | |
| S-DPOModel=Qwen32026.05 | 51.03 | 86.52 | 51.03 | 71.54 | |
| S-DPOModel=SmolLM32026.05 | 45.46 | 87.22 | 45.46 | 69.54 | |
| MASS-DPOModel=SmolLM32026.05 | 44.81 | 87.47 | 44.81 | 69.4 | |
| DPO-kModel=SmolLM32026.05 | 44.16 | 85.91 | 44.16 | 68.09 | |
| DPOModel=Qwen32026.05 | 39.25 | 84.51 | 39.25 | 65.37 | |
| DPOModel=SmolLM32026.05 | 33.33 | 81.75 | 33.33 | 61.01 | |
| DMPOModel=Qwen32026.05 | 26.02 | 74.89 | 26.02 | 53.6 | |
| DMPOModel=SmolLM32026.05 | 26.02 | 75.39 | 26.02 | 53.93 | |
| DMPOModel=Llama32026.05 | 24.36 | 74.99 | 24.36 | 52.84 |