Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factual Prediction on KLAR (all samples)
Loading...
76.08
Accuracy
shortcut method
11.444
28.2245
45.005
61.7855
Apr 5, 2025
Accuracy
Updated 5mo ago
Evaluation Results
Method
Method
Links
Accuracy
shortcut method
Backbone=LLaMA2
2025.04
76.08
fine-tuning
Backbone=LLaMA2, tunin...
2025.04
72.26
original model
Backbone=LLaMA2
2025.04
71.47
translation-en
Backbone=LLaMA2
2025.04
53.88
shortcut method
Backbone=BLOOM
2025.04
51.67
original model
Backbone=BLOOM
2025.04
43.24
fine-tuning
Backbone=BLOOM, tuning...
2025.04
31.73
translation-en
Backbone=BLOOM
2025.04
28.03
translation-early-exit
Backbone=BLOOM
2025.04
15.68
translation-early-exit
Backbone=LLaMA2
2025.04
13.93
Feedback
Search any
task
Search any
task