We would like to thank all the reviewers for writing the insightful comments, especially during this difficult time

Table 1: Starting from one auxiliary task (Exemplar-MT), we keep increasing the number of auxiliary tasks from one to four by adding one Table 2: Effect of ARML on harmful tasks. We would like to thank all the reviewers for writing the insightful comments, especially during this difficult time. By'covered', we mean p(T R1.2 - Our contribution and difference from previous works: Thanks. However, lowering training loss may cause overfitting, especially when training data is scarce. The superiority of ARML is verified in the experiments.