Poetry Generation on Poetry
77.3ScoreRARO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RAROModel size=7B, Reasoning budget=2048 tokens2025.11 | 77.3 | 25 | |
| RAROModel size=3B, Reasoning budget=2048 tokens2025.11 | 71.9 | 17.2 | |
| Iterative DPOModel size=3B, Reasoning budget=2048 tokens2025.11 | 69.8 | 6.6 | |
| RAROModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 67.8 | 7.8 | |
| Iterative DPOModel size=7B, Reasoning budget=2048 tokens2025.11 | 66.5 | 5.1 | |
| SFTModel size=7B, Reasoning budget=2048 tokens2025.11 | 65.4 | 5.9 | |
| RationalizationModel size=7B, Reasoning budget=2048 tokens2025.11 | 57.7 | 5.1 | |
| SFTModel size=3B, Reasoning budget=2048 tokens2025.11 | 57.4 | 2.3 | |
| RL-LogitModel size=7B, Reasoning budget=2048 tokens2025.11 | 55.4 | 3.9 | |
| BaseModel size=7B, Reasoning budget=2048 tokens2025.11 | 54 | 1.2 | |
| SFTModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 53.7 | 2.3 | |
| Iterative DPOModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 48.6 | 0 | |
| RL-LogitModel size=3B, Reasoning budget=2048 tokens2025.11 | 46.9 | 0.4 | |
| BaseModel size=3B, Reasoning budget=2048 tokens2025.11 | 46.5 | 0 | |
| RL-LogitModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 36.4 | 0 | |
| RationalizationModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 35.6 | 0.8 | |
| BaseModel size=1.5B, Reasoning budget=2048 tokens2025.11 | 35 | 0 | |
| RationalizationModel size=3B, Reasoning budget=2048 tokens2025.11 | 30.8 | 0.4 |