Emotional valence classification on OB-GYN (dev)
98.23RecallGatorTron
Evaluation results
| Method | Links | |
|---|---|---|
| GatorTronInput=LP, Training Strategy=Prompt FT2026.02 | 98.23 | |
| Llama-3.2-1BInput=ICL + LP, Training Strategy=Instruction FT2026.02 | 97.4 | |
| BERTInput=LP, Training Strategy=Prompt FT2026.02 | 97.3 | |
| Med42-8BInput=ICL + LP, Training Strategy=Instruction FT2026.02 | 97.09 | |
| GatorTronInput=Anchored, Training Strategy=Prompt FT2026.02 | 96.99 | |
| BERTInput=Anchored, Training Strategy=Prompt FT2026.02 | 96.99 | |
| GatorTronInput=Anchored, Training Strategy=Standard FT2026.02 | 95.85 | |
| Llama-3.2-1BInput=LP, Training Strategy=Instruction FT2026.02 | 95.75 | |
| BERTInput=Anchored, Training Strategy=Standard FT2026.02 | 95.02 | |
| Med42-8BInput=LP, Training Strategy=Instruction FT2026.02 | 94.83 | |
| Med42-70BInput=LP, Training Strategy=Optimized ICL2026.02 | 87.33 | |
| Llama-3.3-70BInput=LP, Training Strategy=Optimized ICL2026.02 | 85.47 | |
| Llama-3.3-70BInput=LP, Training Strategy=Zero-shot2026.02 | 81.46 | |
| Med42-70BInput=LP, Training Strategy=Zero-shot2026.02 | 78.18 | |
| Med42-70BInput=Anchored, Training Strategy=Zero-shot2026.02 | 41.54 | |
| Llama-3.3-70BInput=Anchored, Training Strategy=Zero-shot2026.02 | 38.94 |