ResearchDatasetsAbstainQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSafety EvaluationAbstainQA (test)14.7Accuracy11Safety EvaluationAbstainQA (val)26Accuracy11Selective Question AnsweringAbstainQA (test)13Accuracy11Selective Question AnsweringAbstainQA (val)21Accuracy11