Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Repetition Mitigation on BadCase 30 cases 1 (test)
Loading...
0
Repetition Rate After
Direct Preference Optimization (DPO) fine-tuning
-0.001
-0.0005
0
0.0005
Dec 4, 2025
Repetition Rate After
Repetition Rate Before
Reduction Percentage
Updated 5mo ago
Evaluation Results
Method
Method
Links
Repetition Rate After
Repetition Rate Before
Reduction Percentage
Direct Preference Optimization (DPO) fine-tuning
Hardware=4×A100 GPUs,...
2025.12
0
-
100
Feedback
Search any
task
Search any
task
