ResearchDatasetsUNLIUNLIFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsIntrinsic ReasoningUNLI0.813Spearman Correlation9Scalar probability judgmentUNLI0.057MSE9UMUI Judgment CalibrationUNLI (full)0.057MSE9