Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red Teaming against BB-3B on BAD
Loading...
66.4
RSR
BRT (e+r)
23.552
34.676
45.8
56.924
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
66.4
37.6
BRT (e)
Query limit (NQ)=20,000
2023.05
65.2
39.8
BRT (s+r)
Query limit (NQ)=20,000
2023.05
57.5
40
Offensive Top-NQ
Query limit (NQ)=20,000
2023.05
57.2
40.6
SL
Backbone=OPT-1.3B, Que...
2023.05
52.6
54.9
BRT (s)
Query limit (NQ)=20,000
2023.05
50.2
40.7
SFS
Backbone=Bloom, Query...
2023.05
30.2
44.3
SFS
Backbone=OPT-1.3B, Que...
2023.05
28.6
42.5
Rand
Query limit (NQ)=20,000
2023.05
25.2
42.1
Feedback
Search any
task
Search any
task