ResearchDatasetsDialogue-level evaluationFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDialogue GenerationDialogue-level evaluation Ethical and Affective Alignment8.174Respectful Tone9Dialogue-level Guidance Quality EvaluationDialogue-level evaluation (N=54)3.3State Tracking6