Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sentiment Control on IMDb PosToNeg (test)
Loading...
63.1
Success Rate
PREADD-S
14.948
27.449
39.95
52.451
Jul 6, 2023
Success Rate
Fluency
Relevance/Fidelity
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Fluency
Relevance/Fidelity
PREADD-S
base_model=OPT-6.7B, a...
2023.07
63.1
68.4
25.3
FUDGE
base_model=OPT-6.7B, s...
2023.07
53.2
25.1
31.1
POSPROMPT
base_model=OPT-6.7B, p...
2023.07
30.7
53.5
29.8
G
base_model=OPT-6.7B, d...
2023.07
16.8
51.3
30.6
Feedback
Search any
task
Search any
task