Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction tuning (ICIT) where specific positive or negative examples are incorporated into the prompt for better performance. In this work, we propose PACIT, a simple and effective in-context instruction tuning method, inspired by the pedagogical concept of desirable difficulty. The PACIT method unlocks the power of examples by encouraging the model to actively learn to grasp the distinctions between the positive and negative examples instead of merely reading. The model is expected to first verify the correctness of the provided example according to the task description, which is then set as the condition for generating a better response to the task instance. Our extensive experiments prove the effectiveness of PACIT, outperforming ICIT baseline on both in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores, respectively. Moreover, PACIT can notably enhance the performance of instruction tuning even when all positive and negative examples are generated with a self-instruct method.

翻译：指令微调通过使用有监督的指令数据进行微调，增强了大语言模型的指令遵循能力。先前的研究提出了上下文指令微调（ICIT），将特定的正例或负例纳入提示中以获得更好的性能。在本工作中，我们提出了PACIT，一种受“合意难度”教学理念启发的简单而有效的上下文指令微调方法。PACIT方法通过鼓励模型主动学习掌握正例与负例之间的区别，而非仅仅阅读，从而释放了示例的力量。模型被期望首先根据任务描述验证所提供示例的正确性，然后将其作为为任务实例生成更好响应的条件。我们的大量实验证明了PACIT的有效性，其在领域内和领域外任务上的平均ROUGE-L分数分别比ICIT基线高出最高9.16和3.14。此外，即使所有正例和负例均通过自指令方法生成，PACIT也能显著提升指令微调的性能。