Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Qinhao, Xiang, Xiang, He, Kun, Hopcroft, John E.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916996078108672
author Zhou, Qinhao
Xiang, Xiang
He, Kun
Hopcroft, John E.
author_facet Zhou, Qinhao
Xiang, Xiang
He, Kun
Hopcroft, John E.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
Zhou, Qinhao
Xiang, Xiang
He, Kun
Hopcroft, John E.
Computation and Language
Artificial Intelligence
Machine Learning
Audio and Speech Processing
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.
title Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
topic Computation and Language
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2510.06695