Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Few-shot Natural Language Processing on MetaICL (test)
Loading...
46.1
Classification Score
UnpredicTable-5k
33.724
36.937
40.15
43.363
Aug 1, 2022
Classification Score
LR Score
QA Score
NLI Score
Paraphrasing Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Classification Score
LR Score
QA Score
NLI Score
Paraphrasing Score
UnpredicTable-5k
training_data=Unpredic...
2022.08
46.1
43.7
42.3
36.3
45.7
MetaICL k-shot
training_data=NLP (IID)
2022.08
43.4
-
45.9
-
-
MetaICL k-shot
training_data=NLP (OOD)
2022.08
38.2
43.2
38.7
49
33.1
GPT2
shot_setting=k-shot
2022.08
37.4
38.2
40.2
34
33.7
GPT2
shot_setting=0-shot
2022.08
34.2
34.9
40.4
25.5
34.2
Feedback
Search any
task
Search any
task