Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Objective Generation Evaluation on HH-RLHF (test)
Loading...
1.24
Hypervolume
Bone Soup
0.4184
0.6317
0.845
1.0583
Feb 15, 2025
Hypervolume
Inner Product
Controllability
Length of Front
Sparsity
Spacing
Updated 4d ago
Evaluation Results
Method
Method
Links
Hypervolume
Inner Product
Controllability
Length of Front
Sparsity
Spacing
Bone Soup
Backbone=LLama-2 7B
2025.02
1.24
2.11
100
11
0.33
0.07
Bone Soup
2025.02
1.16
2
1
-
-
-
MOD
Backbone=LLama-2 7B
2025.02
1.08
1.83
100
11
0.24
0.02
Rewarded Soups
Backbone=LLama-2 7B
2025.02
1.06
1.7
84
11
0.24
0.02
MODPO
2025.02
0.93
-0.57
1
-
-
-
Rewards-in-Context
Backbone=LLama-2 7B
2025.02
0.45
1.09
85
8
0.07
0.01
Feedback
Search any
task
Search any
task