Haichao Zhu

Results 2 issues of Haichao Zhu

In Lester et al. (2021), they use T5 as the pre-trained model and use LM head to generate answers. For models like BERT, Roberta explored in this work, we can...

查看huggingface dataset上ALFWorld和Mind2Web的训练数据,发现根据提供的指令,模型不可能产生预期的行为,比如下面两条数据,这个是符合预期的吗?