ResearchDatasetsGSM8K ⊕ HEx-PHIGSM8K ⊕ HEx-PHIFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsBackdoor AttackGSM8K ⊕ HEx-PHI1.8ASR (Without Trigger)8