ResearchDatasetsHaluBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHallucination DetectionHaluBench97AUROC75Hallucination DetectionHaluBench (test)86.96HE14Hallucination EvaluationHaluBench44.6Score13Hallucination DetectionHaluBench73.89Unsafe F1 Score3