ResearchDatasetsIMBDFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHallucination DetectionIMBD (test)0.546AuROC10Dataset AdditionIMBD62Accuracy (5%)5Dataset RemovalIMBD77Accuracy (5% Removal)5Noisy Label DetectionIMBD0.18F1 Score (5% Noise)5