Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Task Evaluation on 9 Downstream Tasks Utility
Loading...
54.7
Average Accuracy
DAPT (nontoxic)
44.508
47.154
49.8
52.446
Feb 8, 2022
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
DAPT (nontoxic)
Backbone=1.3B LM, Eval...
2022.02
54.7
SGEAT (heuristic)
Backbone=1.3B LM, Eval...
2022.02
54.7
Jigsaw (nontoxic)
Backbone=1.3B LM, Eval...
2022.02
54.6
SGEAT (standard)
Backbone=1.3B LM, Eval...
2022.02
54.6
SGEAT (augmented)
Backbone=1.3B LM, Eval...
2022.02
54.4
SGEAT + Rejection Sampling
Backbone=1.3B LM, Eval...
2022.02
54.4
Word Banning
Backbone=1.3B LM, Eval...
2022.02
54.3
Rejection Sampling
Backbone=1.3B LM, Eval...
2022.02
54.3
DEXPERTS
Backbone=1.3B LM, Eval...
2022.02
46.2
SGEAT + DEXPERTS
Backbone=1.3B LM, Eval...
2022.02
44.9
Feedback
Search any
task
Search any
task