ResearchDatasetsControlled Evaluation setFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAbstention and Hallucination EvaluationControlled 50-item Evaluation set epistemic regimes R1–R598Accuracy12
Abstention and Hallucination EvaluationControlled 50-item Evaluation set epistemic regimes R1–R598Accuracy12