ResearchTasksPredictive Validity AssessmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMental Health Task-Oriented Dialogue (TOD) 160K (test)UserSim-160K-it20.818Pearson Correlation (r)8Feb 26, 2026
Mental Health Task-Oriented Dialogue (TOD) 160K (test)UserSim-160K-it20.818Pearson Correlation (r)8Feb 26, 2026