ResearchDatasetsCRUDCRUDFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsQuestion AnsweringCRUD0.555BLEU9Question AnsweringCRUD Two-hop (test)23.82BLEU-17Question AnsweringCRUD Single-hop (test)0.375BLEU-17