ResearchDatasetsPreference OptimizationPreference OptimizationFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMachine TranslationPreference Optimization Machine Translation0.25Reward2SummarizationPreference Optimization Summarization0.3Reward2Conversational AssistantPreference Optimization Conversational0.28Reward2