Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Style Transfer on Anime-style dialogue human evaluation set (test)
Loading...
4.24
Semantic Coherence Score
Model v2
3.4392
3.6471
3.855
4.0629
Mar 6, 2026
Semantic Coherence Score
Style Adherence Score
Overall Quality Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Semantic Coherence Score
Style Adherence Score
Overall Quality Score
Model v2
Inference protocol=Inf...
2026.03
4.24
3.51
3.47
Baseline D
Approach=Prompt-based
2026.03
4.03
4.4
3.88
Baseline C
Training=Vanilla SFT
2026.03
3.47
3.6
3.18
Feedback
Search any
task
Search any
task