ResearchDatasetsHH and UFHH and UFFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPreference AlignmentHH and UF Out-of-Domain (test)58.7OOD Win Rate10Preference AlignmentHH and UF In-Domain (test)68.4Win Rate10