Harmlessness evaluation on HH-RLHF (test)
83.33Win Rate
APL
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.05 | 83.33 | - | 0.43 | 2.6 | |
2025.05 | 80 | - | 1.3 | 1.9 | |
2025.05 | 76.67 | - | 0.69 | 2.28 | |
2025.05 | 71.67 | - | 2.12 | 1.38 | |
2025.05 | 70 | - | 1.9 | 1.46 | |
2025.05 | 56.67 | - | 1.34 | 2.09 | |
2025.05 | 54.17 | - | 1.69 | 1.97 | |
2025.05 | 52.5 | - | 1.34 | 1.99 | |
2025.05 | 51 | - | 2.08 | 2.05 | |
2025.05 | 50.83 | - | 1.56 | 1.9 | |
2025.05 | 50 | - | 5.88 | 0.38 | |
2025.05 | 50 | - | 1.95 | 2.02 | |
2024.02 | - | 40 | - | - | |
2024.02 | - | 43 | - | - | |
2024.02 | - | 47 | - | - | |
2024.02 | - | 40 | - | - | |
2024.02 | - | 57 | - | - | |
2024.02 | - | 37 | - | - | |
2024.02 | - | 67 | - | - |