ResearchDatasetsXSum, SamSum, CNN, WMT, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSMFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSelective GenerationXSum, SamSum, CNN, WMT19, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSM8k Aggregate0.814Mean ROC-AUC22
Selective GenerationXSum, SamSum, CNN, WMT19, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSM8k Aggregate0.814Mean ROC-AUC22