ResearchTasksShort-text Multi-doc Question AnsweringShort-text Multi-doc Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRGB noise robustness testbed (test)Our model (PAM QA)96EM (Noise 0)6Feb 26, 2026