Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Headline Generation on Blind N ≈ 5000 (test)
Loading...
2.07
Mean Rating Improvement (%)
PROPOSED SC-MLM
-10.3476
-7.1238
-3.9
-0.6762
Jul 7, 2026
Mean Rating Improvement (%)
Improvement in Count (Rating ≥ 2/3) (%)
Improvement in Count (Rating = 3/3) (%)
Updated 17d ago
Evaluation Results
Method
Method
Links
Mean Rating Improvement (%)
Improvement in Count (Rating ≥ 2/3) (%)
Improvement in Count (Rating = 3/3) (%)
PROPOSED SC-MLM
training_type=Self-Cri...
2026.07
2.07
2.37
6.53
PROPOSED MLM
input_mode=Multiple Pr...
2026.07
1.15
2.42
1.22
MLM - SINGLE PRODUCT
input_mode=Single Product
2026.07
0.4
2.75
-0.06
SC-BILSTM
training_type=Self-Cri...
2026.07
-9.87
-4.99
-42.96
Feedback
Search any
task
Search any
task