ResearchDatasetsChatbotFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Utility EvaluationChatbot80Agree Score14Dialogue ManagementChatbot (unseen states)0.85Reward4Open-domain dialogueChatbot77.8Accuracy2