This work proposes a challenging yet more realistic setting for zero-shot cross-task generalization: zero-shot instruction following, presuming the existence of a paragraph-style task definition while no demonstrations exist. To better learn the task supervision from the definition, we propose two strategies: first, to automatically find out the critical sentences in the definition; second, a ranking objective to force the model to generate the gold outputs with higher probabilities when those critical parts are highlighted in the definition. The joint efforts of the two strategies yield state-of-the-art performance on the Super-NaturalInstructions. Our code is available on GitHub.

翻译：本文提出了一种更具挑战性但更符合实际的零样本跨任务泛化设定：零样本指令跟随，该设定假设任务定义以段落形式存在，但没有任何示范样例。为了更好地从定义中学习任务监督信号，我们提出两种策略：首先，自动识别定义中的关键句子；其次，引入排序目标，迫使模型在定义中关键部分被强调时，以更高概率生成标准输出。这两种策略的协同作用在Super-NaturalInstructions上取得了最先进的性能。我们的代码已在GitHub上开源。