ResearchTasksTruthfulness and Calibration EvaluationTruthfulness and Calibration EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCross-LVLM Pooled Average (GQA, POPE, etc.)BICR7.1ECE8May 12, 2026