Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Compositional Reasoning on Compositional Reasoning Paraphrasing Input Ip
Loading...
70.5
Event Probability p(Ac) > p(Aw)
CREME
34.308
43.704
53.1
62.496
Feb 22, 2024
Event Probability p(Ac) > p(Aw)
Updated 4d ago
Evaluation Results
Method
Method
Links
Event Probability p(Ac) > p(Aw)
CREME
Backbone=OpenAlpaca-3B
2024.02
70.5
CREME
Backbone=LLAMA-2-7B
2024.02
52.9
Memory Injection
Backbone=OpenAlpaca-3B
2024.02
43.8
Original
Backbone=OpenAlpaca-3B
2024.02
42.7
Memory Injection
Backbone=LLAMA-2-7B
2024.02
40.3
Original
Backbone=LLAMA-2-7B
2024.02
35.7
Feedback
Search any
task
Search any
task