Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks

In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. Prompts for LLMs generally comprise two components: the textitinstruction, which defines the task or objective, and the textitinput, which is tailored to the instruction type. In natural language generation (NLG) tasks such as machine translation, the textitinput component is particularly critical, while the textitinstruction component tends to be concise. Existing prompt engineering methods primarily focus on optimizing the textitinstruction component for general tasks, often requiring large-parameter LLMs as auxiliary tools. However, these approaches exhibit limited applicability for tasks like machine translation, where the textitinput component plays a more pivotal role. To address this limitation, this paper introduces a novel prompt optimization method specifically designed for machine translation tasks. The proposed approach employs a small-parameter model trained using a back-translation-based strategy, significantly reducing training overhead for single-task optimization while delivering highly effective performance. With certain adaptations, this method can also be extended to other downstream tasks.