Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Factuality Evaluation on FactScore (labeled)
Loading...
64.8
LS Score (%)
PaCE
14.256
27.378
40.5
53.622
Jun 6, 2024
LS Score (%)
LAF Score
Updated 4d ago
Evaluation Results
Method
Method
Links
LS Score (%)
LAF Score
PaCE
Target Model=LLaMA2-13...
2024.06
64.8
53
Prompting
Target Model=LLaMA2-13...
2024.06
61.6
24.5
OrthoProj
Target Model=LLaMA2-13...
2024.06
59.3
52.8
Vanilla
Target Model=LLaMA2-13...
2024.06
44.1
39.6
Prompting
Target Model=LLaMA2-7B...
2024.06
28.6
40.6
PaCE
Target Model=LLaMA2-7B...
2024.06
27.7
65.9
VecAdd
Target Model=LLaMA2-13...
2024.06
24.5
49.2
OrthoProj
Target Model=LLaMA2-7B...
2024.06
21.9
49.7
Vanilla
Target Model=LLaMA2-7B...
2024.06
18.4
45.1
VecAdd
Target Model=LLaMA2-7B...
2024.06
16.2
46.1
Feedback
Search any
task
Search any
task