Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Summarization on CNN/DM (R-1, R-2, R-L, Fact)
Loading...
45.1
ROUGE-1
Base model
44.1952
44.4301
44.665
44.8999
Jun 16, 2023
ROUGE-1
ROUGE-2
ROUGE-L
Factuality Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROUGE-1
ROUGE-2
ROUGE-L
Factuality Score
Base model
Reward Optimized=MLE (...
2023.06
45.1
21.76
41.86
15.57
Semi-offline RL
Reward Optimized=Factu...
2023.06
44.6
21.66
41.91
18.3
BRIO
Reward Optimized=Factu...
2023.06
44.23
21.18
40.92
17.54
AVG
Reward Optimized=Factu...
2023.06
44.23
21.24
40.93
17.68
Feedback
Search any
task
Search any
task