ResearchBenchmarksCommonsense Question Answering on Scientific Commonsense (QASC) 1.0 (test)Commonsense Question Answering on Scientific Commonsense (QASC) 1.0 (test)Follow53.04AccuracyGPT-344.907247.018649.1351.2414Sep 2, 2022Evaluation resultsMethodMethodLinksAccuracyGPT-3Answer predictor=T5-largeAnswer predictor=T5-large2022.0953.04ELABORAnswer predictor=T5-la...Answer predictor=T5-large, Elaboration model=GPT2-large2022.0950.22pipelineAnswer predictor=T5-la...Answer predictor=T5-large, Elaboration model=GPT2-large2022.0949.13selftalkAnswer predictor=T5-largeAnswer predictor=T5-large2022.0946.85vanillaAnswer predictor=T5-largeAnswer predictor=T5-large2022.0945.22