Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red Teaming against BB-3B on Bloom ZS
Loading...
4,120
RSR
BRT (e+r)
-81.6
1,009.2
2,100
3,190.8
May 27, 2023
RSR
Self-BLEU (k)
Updated 4d ago
Evaluation Results
Method
Method
Links
RSR
Self-BLEU (k)
BRT (e+r)
Query limit (NQ)=20,000
2023.05
4,120
46.2
BRT (e)
Query limit (NQ)=20,000
2023.05
3,910
48.6
BRT (s+r)
Query limit (NQ)=20,000
2023.05
1,240
50.8
SL
Backbone=OPT-1.3B, Que...
2023.05
1,200
58.9
BRT (s)
Query limit (NQ)=20,000
2023.05
1,030
50.8
Offensive Top-NQ
Query limit (NQ)=20,000
2023.05
780
51.9
SFS
Backbone=OPT-1.3B, Que...
2023.05
740
49.6
SFS
Backbone=Bloom, Query...
2023.05
540
50.1
Rand
Query limit (NQ)=20,000
2023.05
80
51.6
Feedback
Search any
task
Search any
task