Detoxification on REALTOXICITYPROMPTS (test)
0.081Toxicity Score (Avg)
FINE-GRAINED RLHF
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2023.06 | 0.081 | 9.77 | 94.9 | 93.2 | |
2023.06 | 0.13 | 11.75 | 94.3 | 92.6 | |
2023.06 | 0.136 | 22.83 | 93.2 | 92.2 | |
2023.06 | 0.154 | 24.78 | 93.8 | 93.8 | |
2023.06 | 0.192 | 9.58 | 94.7 | 93.1 |