List your company

Machine Translation on Preference Optimization Machine Translation

0.25RewardZOPrO
0.1460.1730.20.227Mar 5, 2025

Evaluation results

MethodLinks
ZOPrOModel=Gemma 2, Parameters=2.4B2025.030.25
ZOPrOModel=Qwen 2.5, Parameters=1.5B2025.030.15