{"ID":2858602,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06695","arxiv_id":"2510.06695","title":"Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks","abstract":"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 \\textit{instruction}, which defines the task or objective, and the \\textit{input}, which is tailored to the instruction type. In natural language generation (NLG) tasks such as machine translation, the \\textit{input} component is particularly critical, while the \\textit{instruction} component tends to be concise. Existing prompt engineering methods primarily focus on optimizing the \\textit{instruction} 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 \\textit{input} 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.","short_abstract":"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 \\textit{instruction}, which defines the task or objective, and the \\textit{input}, wh...","url_abs":"https://arxiv.org/abs/2510.06695","url_pdf":"https://arxiv.org/pdf/2510.06695v1","authors":"[\"Qinhao Zhou\",\"Xiang Xiang\",\"Kun He\",\"John E. Hopcroft\"]","published":"2025-10-08T06:40:06Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\",\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}