Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Generation on Human Evaluation 100 dialogue contexts (test)
Loading...
19
Fluency (Win)
DialogVED-Sampling
15.88
16.69
17.5
18.31
Apr 27, 2022
Fluency (Win)
Fluency (Lose)
Coherence (Win)
Coherence (Lose)
Informativeness (Win)
Informativeness (Lose)
Overall (Win)
Overall (Lose)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Fluency (Win)
Fluency (Lose)
Coherence (Win)
Coherence (Lose)
Informativeness (Win)
Informativeness (Lose)
Overall (Win)
Overall (Lose)
DialogVED-Sampling
Comparison Group=Group...
2022.04
19
13
22
24
31
14
24
17
DialogVED
Comparison Group=Group...
2022.04
16
11
38
16
13
11
26
14
Feedback
Search any
task
Search any
task