ResearchBenchmarksMachine Translation on Preference Optimization Machine TranslationFollow0.25RewardZOPrO0.1460.1730.20.227Mar 5, 2025Evaluation ResultsMethodMethodLinksRewardZOPrOModel=Gemma 2, Paramet...Model=Gemma 2, Parameters=2.4B2025.030.25ZOPrOModel=Qwen 2.5, Parame...Model=Qwen 2.5, Parameters=1.5B2025.030.15