ResearchDatasetsTriviaQA, HotpotQA, and MedMCQATriviaQA, HotpotQA, and MedMCQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAnswer correctness predictionTriviaQA, HotpotQA, and MedMCQA In-Distribution Average (val)0.91Head Entropy12Answer correctness predictionTriviaQA, HotpotQA, and MedMCQA OOD Generalization Average (val)0.68Head Entropy6
Answer correctness predictionTriviaQA, HotpotQA, and MedMCQA In-Distribution Average (val)0.91Head Entropy12
Answer correctness predictionTriviaQA, HotpotQA, and MedMCQA OOD Generalization Average (val)0.68Head Entropy6