ResearchDatasetsCultureFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSycophancy DetectionCulture Dataset98.3Accuracy12Text-to-Image Factuality EvaluationCulture 3089.4FAGER6Factual A/B testCulture 30 pairs (test)97Pairwise Accuracy3