ResearchDatasetsTRUETRUEFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsFactual Consistency EvaluationTRUE benchmark98.4PAWS (AUC-ROC)37Factual Consistency EvaluationTRUE 1.0 (test)91.5Frank AUC20Factual Grounding EvaluationTRUE (sampled 100 entries from each of 11 datasets)0.86ROC-AUC3