Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red Teaming against BB-3B on OPT-66B ZS
Loading...
72.3
RSR
BRT (e+r)
1.476
19.863
38.25
56.637
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
72.3
45.3
BRT (e)
Query limit (NQ)=20,000
2023.05
70.8
46.4
SL
Backbone=OPT-1.3B, Que...
2023.05
41.9
55.4
Offensive Top-NQ
Query limit (NQ)=20,000
2023.05
41.5
52.2
SFS
Backbone=OPT-1.3B, Que...
2023.05
33.4
50
SFS
Backbone=Bloom, Query...
2023.05
30.5
50.1
BRT (s+r)
Query limit (NQ)=20,000
2023.05
12.5
51
BRT (s)
Query limit (NQ)=20,000
2023.05
11.4
44.3
Rand
Query limit (NQ)=20,000
2023.05
4.2
47.3
Feedback
Search any
task
Search any
task