ResearchTasksConversational AssistantFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHH-RLHFRLOO0.5Reward3Feb 26, 2026Preference Optimization ConversationalZOPrO0.28Reward2Feb 26, 2026