Preference Alignment on OpenRLHF Mixture
7.6Reward
AAD
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.09 | 7.6 | - | |
2025.09 | 7.28 | - | |
2025.09 | 6.84 | 0.67 | |
2025.09 | 6.26 | - | |
2025.09 | 6.18 | 0.72 | |
2025.09 | 5.88 | 57 | |
2025.09 | 5.6 | 0.85 | |
2025.09 | 5.45 | - | |
2025.09 | 5.34 | 0.83 | |
2025.09 | 5.29 | 0.54 | |
2025.09 | 5.24 | 70 | |
2025.09 | 4.93 | 0.89 | |
2025.09 | 4.91 | 73 | |
2025.09 | 4.54 | 0.88 | |
2025.09 | 4.48 | 0.69 | |
2025.09 | 4.07 | 51 | |
2025.09 | 4.04 | - | |
2025.09 | 3.89 | 0.93 | |
2025.09 | 3.64 | 57 | |
2025.09 | 3.59 | 82 | |
2025.09 | 3.59 | 0.9 | |
2025.09 | 3.56 | 0.79 | |
2025.09 | 3.42 | - | |
2025.09 | 3.15 | 63 | |
2025.09 | 3.08 | 0.55 | |
2025.09 | 2.63 | 0.88 | |
2025.09 | 2.42 | 0.68 | |
2025.09 | 2.06 | 72 | |
2025.09 | 1.74 | 0.76 | |
2025.09 | 0.83 | 0.83 |