ResearchDatasetsFELMFELMFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoning FactualityFELM99.19Coverage20Hallucination DetectionFELM worldknowledge (test)88.3Nonfact Accuracy15Hallucination DetectionFELM48.3F1 Score8