Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Personalized Text Generation on LaMP-4 time-based split (dev)
Loading...
21
ROUGE-1
Raw Hist.
15.8
17.15
18.5
19.85
Jun 3, 2026
ROUGE-1
ROUGE-L
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROUGE-1
ROUGE-L
Raw Hist.
User representation=No...
2026.06
21
19.4
Direct Reward
User representation=Ta...
2026.06
20
18.2
BUMP+
User representation=Se...
2026.06
19.9
18
BUMP
User representation=Se...
2026.06
19.7
17.9
Gemini-3 Pro
User representation=Ze...
2026.06
19.5
17.8
Qwen3-4B (ZS)
User representation=Ze...
2026.06
18.3
16.6
Gemini-3 Flash
User representation=Ze...
2026.06
18.1
16.4
No Pers.
User representation=No...
2026.06
16
14.1
Feedback
Search any
task
Search any
task