ResearchTasksInterpretation AlignmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAmbrosia sampled 30 ambiguous examplesIntentRL0.917Alignment Score1Feb 26, 2026Abg-CoQA (sampled 30 ambiguous examples)IntentRL90Alignment1Feb 26, 2026