ResearchDatasetsHH-RLHF and IMDBHH-RLHF and IMDBFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsText GenerationHH-RLHF and IMDB7.12Helpful Assistant Score16Text GenerationHH-RLHF and IMDB (test)3.2Total Training Time (h)6