ResearchTasksLong-form QA Factuality DetectionFor AI assistantsMarkdownContent indexLong-form QA Factuality DetectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLong-form QA benchmark factuality targetFRANQ condition-calibrated17.3PR-AUC48Apr 20, 2026