Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Repetition Mitigation on BadCase 2 (test)
Loading...
60
Repetition Rate Before
Direct Preference Optimization (DPO) fine-tuning
57
58.5
60
61.5
Dec 4, 2025
Repetition Rate Before
Repetition Rate After
Repetition Rate Reduction
Updated 5mo ago
Evaluation Results
Method
Method
Links
Repetition Rate Before
Repetition Rate After
Repetition Rate Reduction
Direct Preference Optimization (DPO) fine-tuning
Hardware=4×A100 GPUs,...
2025.12
60
2
96.7
Feedback
Search any
task
Search any
task
