ResearchDatasetsPreference OptimizationFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMachine TranslationPreference Optimization Machine Translation0.25Reward2SummarizationPreference Optimization Summarization0.3Reward2Conversational AssistantPreference Optimization Conversational0.28Reward2