Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue on Dialogue (test)
Loading...
8.84
Fluency
SFT
8.372
8.4935
8.615
8.7365
Jun 21, 2024
Fluency
Accuracy
Toxicity
Helpfulness
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Fluency
Accuracy
Toxicity
Helpfulness
Overall Score
SFT
Backbone=LLaMA2-13B
2024.06
8.84
7.77
8.49
7.43
7.31
HBAT
Backbone=LLaMA2-13B, O...
2024.06
8.8
7.7
8.48
7.39
7.89
HBAT
Backbone=LLaMA2-13B, O...
2024.06
8.79
7.8
8.45
7.51
7.96
DPO
Backbone=LLaMA2-13B, O...
2024.06
8.67
7.13
8.54
7.63
7.84
RLHF
Backbone=LLaMA2-13B, O...
2024.06
8.39
7.62
8.87
7.47
7.72
Feedback
Search any
task
Search any
task
