Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generative QA on TweetQA Cyrillic noise (test)
Loading...
41.2
F1 Score
SDBN-p
20.4
25.8
31.2
36.6
Jun 9, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
SDBN-p
Backbone=LLaMA-3.2-1B,...
2026.06
41.2
EDA
Backbone=LLaMA-3.2-1B,...
2026.06
33.4
NEFTune
Backbone=LLaMA-3.2-1B,...
2026.06
33
Vanilla
Backbone=LLaMA-3.2-1B,...
2026.06
26.8
SMART
Backbone=LLaMA-3.2-1B,...
2026.06
21.2
Feedback
Search any
task
Search any
task
