ResearchDatasetsSynthetic ConversationsSynthetic ConversationsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPredicting human judges' overall quality (Q0)Synthetic Conversations (5-fold cross-evaluation)0.611Pearson's r12
Predicting human judges' overall quality (Q0)Synthetic Conversations (5-fold cross-evaluation)0.611Pearson's r12