ResearchTasksLong-form generation factuality and uncertainty estimationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWildHallu (test)LOGU-DPO0.86Factuality Score14Feb 26, 2026LongFact (test)LOGU-DPO91.5Factuality Score14Feb 26, 2026Bios (test)LOGU-DPO71.4FA14Feb 26, 2026