ResearchDatasetsYouCook and CraftBenchYouCook and CraftBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAutomatic Metric Correlation with Human Factual Correctness JudgmentsYouCook3-Fact and CraftBench-Fact (User Study)0.534Pearson r8
Automatic Metric Correlation with Human Factual Correctness JudgmentsYouCook3-Fact and CraftBench-Fact (User Study)0.534Pearson r8