ResearchDatasetsMACEMACEFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsConfidence CalibrationMACE (test)81.2AUROC84Model CalibrationMACE82.4AUROC84LLM CalibrationMACE8.6ECE60MACE PredictionMACE Prediction n=350 (test)81.8AUROC1