ResearchDatasetsDollyEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsInstruction FollowingDollyEval32.5Rouge-L114Instruction followingDollyEval 500 (test)31.3Rouge-L24Dialogue GenerationDollyEval24.19ROUGE-L16GenerationDollyEval (test)62.02LLM-as-a-Judge Score2Instruction FollowingDollyEval (test)—ScoreInstruction Following on DollyEval (test) performance trend0
Instruction FollowingDollyEval (test)—ScoreInstruction Following on DollyEval (test) performance trend0