ResearchBenchmarksCommonsense Reasoning on CoS-E v1.11Follow0.608Score (Finetune+Baseline vs Predict+Baseline)T5-base0.43640.480950.52550.57005May 4, 2023Evaluation ResultsMethodMethodLinksScore (Finetune+Baseline vs Predict+Baseline)Score (Finetune+Baseline vs Predict+Infusion)Simulatability ScoreScore (Finetune+Infusion vs Predict+Infusion)TREU ScoreT5-baseBackbone=T5-baseBackbone=T5-base2023.050.6080.610.0020.8030.197BART-baseBackbone=BART-baseBackbone=BART-base2023.050.4430.4490.0060.70.263