ResearchTasksDialogue Policy EvaluationDialogue Policy EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPersonaChat (test)FIXED97.7USR RET10Feb 26, 2026Empathetic Dialogues (test)FIXED0.912USR MLM8Feb 26, 2026Dailydialog (test)PARROT81.1USR MLM8Feb 26, 2026