Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Generation on Vicuna (test)
Loading...
19.4
ROUGE-L
Teacher
13.16
14.78
16.4
18.02
Mar 4, 2026
ROUGE-L
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROUGE-L
Teacher
Model=LLaMA, #Params=13B
2026.03
19.4
VQAE
Model=LLaMA, #Params=7B
2026.03
18.7
KD
Model=LLaMA, #Params=7B
2026.03
18.4
SeqKD
Model=LLaMA, #Params=7B
2026.03
18.1
SFT w/o KD
Model=LLaMA, #Params=7B
2026.03
17.5
KD
Model=GPT-2, #Params=760M
2026.03
16.9
Teacher
Model=GPT-2, #Params=1.5B
2026.03
16.3
VQAE
Model=GPT-2, #Params=760M
2026.03
16.3
SFT w/o KD
Model=GPT-2, #Params=760M
2026.03
16.1
SeqKD
Model=GPT-2, #Params=760M
2026.03
15.9
VQAE
Model=GPT-2, #Params=120M
2026.03
15.2
SFT w/o KD
Model=GPT-2, #Params=120M
2026.03
14.7
SeqKD
Model=GPT-2, #Params=120M
2026.03
14.3
KD
Model=GPT-2, #Params=120M
2026.03
13.4
Feedback
Search any
task
Search any
task