ResearchDatasetsFavaFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLong-form Question AnsweringFAVA FullP (100% polluted)82.54VeriScore F1@k26Long-form Question AnsweringFAVA MixP (50% polluted)91.59VeriScore F1@k26Hallucination detectionFAVA Annotated Dataset83.28AUCROC16Long-form Question AnsweringFava61VeriScore F114