Safety Classification on Bloom safety filter benchmark 100 examples (test)
100AccuracyBloom Safety Filter
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Bloom Safety FilterCategory=4: Neg. Mindsets, Evaluation protocol=Strict, Temperature=02025.10 | 100 | 100 | 100 | 100 | |
| Bloom Safety FilterCategory=5: Inacc. Advice, Evaluation protocol=Strict, Temperature=02025.10 | 95 | 91 | 100 | 95 | |
| Bloom Safety FilterCategory=2: Body Image, Evaluation protocol=Strict, Temperature=02025.10 | 91 | 84 | 100 | 91 | |
| Bloom Safety FilterCategory=1: Bodily Harm, Evaluation protocol=Strict, Temperature=02025.10 | 90 | 92 | 88 | 90 | |
| Bloom Safety FilterCategory=Overall, Evaluation protocol=Strict, Temperature=02025.10 | 85 | 78 | 96 | 86 | |
| Bloom Safety FilterCategory=Overall, Evaluation protocol=Relaxed, Temperature=02025.10 | 85 | 78 | 96 | 86 | |
| Bloom Safety FilterCategory=3: Mental Health, Evaluation protocol=Strict, Temperature=02025.10 | 80 | 75 | 90 | 82 |