ResearchBenchmarksOpen-ended Text Generation on WritingPrompts (test)Follow85Same CountMIXCE80.7582.8758587.125May 26, 2023Evaluation ResultsMethodMethodLinksSame CountMixCE CountMLE CountMIXCEBackbone=GPT-2 large,...Backbone=GPT-2 large, Decoding=unbiased sampling, Evaluation protocol=blind A/B testing2023.0585111—MLEBackbone=GPT-2 large,...Backbone=GPT-2 large, Decoding=unbiased sampling, Evaluation protocol=blind A/B testing2023.0585—119