Reward Model Transfer on UltraFeedback (UF)
7.93AOG
ANCHOR
Updated 8d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 7.93 | - | - | 7.93 | |
2026.05 | 7.64 | - | - | 5.52 | |
2026.05 | 6.25 | - | - | -9.42 | |
2026.05 | 5.79 | - | - | -5.8 | |
2026.05 | 5.73 | - | - | 5.73 | |
2026.05 | 5.61 | - | - | 5.61 | |
2026.05 | 5.49 | - | - | 2.07 | |
2026.05 | 5.15 | - | - | 5.15 | |
2026.05 | 4.98 | - | - | 4.98 | |
2026.05 | 4.92 | - | - | 4.92 | |
2026.05 | 4.8 | - | - | 4.8 | |
2026.05 | 4.74 | - | - | 4.74 | |
2026.05 | 4.69 | - | - | 4.69 | |
2026.05 | 4.4 | - | - | 2.1 | |
2026.05 | 0.17 | - | - | -2.89 | |
2026.05 | -0.46 | - | - | -13.5 | |
2026.05 | - | 73.4 | 1.74 | - | |
2026.05 | - | 41.8 | 0.99 | - | |
2026.05 | - | -280.6 | -6.65 | - | |
2026.05 | - | 97.9 | 2.32 | - | |
2026.05 | - | -89.1 | -0.41 | - | |
2026.05 | - | -39.1 | -0.18 | - | |
2026.05 | - | -517.4 | -2.38 | - | |
2026.05 | - | 189.1 | 0.87 | - |