Persuasion on args.me corpus Persuadee: Phi-4 OOD
31.13Agreement ShiftDS-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| DS-R1Size=671B2025.05 | 31.13 | |
| LLaMa3.2 + RLSize=3B2025.05 | 29.87 | |
| Gemma-3Size=27B2025.05 | 28.07 | |
| LLaMa3.2 + ToMAPSize=3B2025.05 | 27 | |
| Qwen2.5 + SFTSize=3B2025.05 | 22.98 | |
| Qwen2.5 + ToMAPSize=3B2025.05 | 22.25 | |
| GPT-4oSize=N/A2025.05 | 22.06 | |
| Qwen2.5Size=3B2025.05 | 21.74 | |
| LLaMa3.1Size=70B2025.05 | 21.29 | |
| LLaMa3.2 + SFTSize=3B2025.05 | 20.95 | |
| LLaMa3.2Size=3B2025.05 | 19.97 | |
| Qwen2.5 + RLSize=3B2025.05 | 15.51 |