Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spoken Question Answering on LongAudio
Loading...
31.12
BLEU
+LEAF
7.5536
13.6718
19.79
25.9082
May 29, 2026
BLEU
ROUGE-1
ROUGE-2
ROUGE-L
METEOR
F1 Score (Boundary)
Predicted Token Coverage
Likert Score (1-5)
DA Score (0-100)
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU
ROUGE-1
ROUGE-2
ROUGE-L
METEOR
F1 Score (Boundary)
Predicted Token Coverage
Likert Score (1-5)
DA Score (0-100)
+LEAF
Backbone=Granite 3 2B
2026.05
31.12
56.24
37.56
50.27
50.62
92.63
30.2
2.93
70.21
+LoRA GRPO
Backbone=Granite 3 2B
2026.05
22.44
49.6
31.77
43.56
45.59
90.83
40.5
2.43
67.11
base
Backbone=Granite 3 2B
2026.05
8.46
31.01
13.91
23.67
34.76
86.7
70.1
2.01
66.61
Feedback
Search any
task
Search any
task