Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Entailment tree generation on EntailmentBank (test)
Loading...
45.6
Leaves F1
IRGR
34.368
37.284
40.2
43.116
May 4, 2023
Leaves F1
Leaves AllCorrect
Step Structures F1
Step Structures AllCorrect
Intermediates F1
Intermediates AllCorrect
Overall AllCorrect
Updated 4d ago
Evaluation Results
Method
Method
Links
Leaves F1
Leaves AllCorrect
Step Structures F1
Step Structures AllCorrect
Intermediates F1
Intermediates AllCorrect
Overall AllCorrect
IRGR
Backbone=T5-large
2023.05
45.6
11.8
16.1
11.4
38.8
20.9
11.5
NLProofs
Backbone=T5-large
2023.05
43.2
8.2
11.2
6.9
42.9
17.3
6.9
RLET
Backbone=DeBERTa-large
2023.05
38.3
9.1
11.5
7.1
34.2
12.1
6.9
EntailmentWriter
Backbone=T5-large
2023.05
35.7
2.9
6.1
2.4
33.4
7.7
2.4
MetGen
Backbone=T5-large
2023.05
34.8
8.7
9.8
8.6
36.6
20.4
8.6
Feedback
Search any
task
Search any
task