ResearchDatasets2WikiQA2WikiQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-hop Question Answering2WikiQA (test)74.3F171Question Answering2WikiQA (test)57.9EM24Multi-hop Question Answering2WikiQA OOD evaluation38.76EM6Multi-hop Question Answering2WikiQA0.44Latency (s)6Retrieval2WikiQA0.15Average Running Time (s)5Question Answering2WikiQA53.1EM4