ResearchTasksGenerative Hallucination EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAMBER (test)SID7.9CHAIR Score18May 28, 2026AMBERACPO90.79Score14Apr 7, 2026