Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Personalized news headline generation on LaMP
Loading...
16.1
ROUGE-L (Average)
PerCE
12.252
13.251
14.25
15.249
Jan 24, 2026
Jan 25, 2026
Jan 27, 2026
Jan 29, 2026
Jan 31, 2026
Feb 2, 2026
Feb 4, 2026
ROUGE-L (Average)
ROUGE-L (Qwen2.5 1.5B)
ROUGE-L (Gemma3 1B)
ROUGE-L (StableLM2 1.6B)
METEOR
Updated 2mo ago
Evaluation Results
Method
Method
Links
ROUGE-L (Average)
ROUGE-L (Qwen2.5 1.5B)
ROUGE-L (Gemma3 1B)
ROUGE-L (StableLM2 1.6B)
METEOR
PerCE
Backbone=Qwen3-4B
2026.02
16.1
-
-
-
17.9
CE
Backbone=Qwen3-4B
2026.02
15.3
-
-
-
16.5
clustering-driven memory compression
Number of memory token...
2026.01
13.99
15.16
13.45
13.36
-
Concat
Number of memory token...
2026.01
13.8
15.34
13.91
12.14
-
Mean
Number of memory token...
2026.01
12.4
12.79
12.37
12.05
-
Feedback
Search any
task
Search any
task