Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multilingual Question Answering on TydiQA (F1 score)
Loading...
48.71
F1 Score
Forgetting
33.6924
37.5912
41.49
45.3888
Aug 6, 2025
F1 Score
Updated 19d ago
Evaluation Results
Method
Method
Links
F1 Score
Forgetting
Base model=LLaMA-2-13B...
2025.08
48.71
Ignoring
Base model=LLaMA-2-13B...
2025.08
38.39
Full Tokens (standard SFT)
Base model=LLaMA-2-13B...
2025.08
36.77
Base
Base model=LLaMA-2-13B...
2025.08
34.27
Feedback
Search any
task
Search any
task