Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Lexically constrained decoding on CommonGen
Loading...
4.24
Count
COLD
2.6592
3.0696
3.48
3.8904
Feb 23, 2022
Count
Percent
PPL
Human Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Count
Percent
PPL
Human Score
COLD
2022.02
4.24
94.5
54.98
2.07
NEUROLOGIC
2022.02
3.3
91
28.61
2.53
TSMH
2022.02
2.72
71.27
1,545.15
1.72
Feedback
Search any
task
Search any
task