Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red Teaming on Bloom ZS (filtered hard positive)
Loading...
15.6
RSR
BRT (e+r)
0
4.05
8.1
12.15
May 27, 2023
RSR
Self-BLEU(k)
Updated 4d ago
Evaluation Results
Method
Method
Links
RSR
Self-BLEU(k)
BRT (e+r)
Target Model=BB-3B, Qu...
2023.05
15.6
0.457
BRT (s+r)
Target Model=BB-3B, Qu...
2023.05
6.4
0.501
SL
Target Model=BB-3B, Qu...
2023.05
5.4
0.604
SFS
Target Model=BB-3B, Qu...
2023.05
3.3
0.514
Offensive Top-NQ
Target Model=BB-3B, Qu...
2023.05
3.1
0.502
SFS
Target Model=BB-3B, Qu...
2023.05
2.6
0.523
Rand
Target Model=BB-3B, Qu...
2023.05
0.6
0.519
Feedback
Search any
task
Search any
task