Standard-to-dialect machine translation remains challenging due to a persistent dialect gap in large language models and evaluation distortions inherent in n-gram metrics, which favor source copying over authentic dialect translation. In this paper, we propose the dialect refinement (DIA-REFINE) framework, which guides LLMs toward faithful target dialect outputs through an iterative loop of translation, verification, and feedback using external dialect classifiers. To address the limitations of n-gram-based metrics, we introduce the dialect fidelity score (DFS) to quantify linguistic shift and the target dialect ratio (TDR) to measure the success of dialect translation. Experiments on Korean dialects across zero-shot and in-context learning baselines demonstrate that DIA-REFINE consistently enhances dialect fidelity. The proposed metrics distinguish between False Success cases, where high n-gram scores obscure failures in dialectal translation, and True Attempt cases, where genuine attempts at dialectal translation yield low n-gram scores. We also observed that models exhibit varying degrees of responsiveness to the framework, and that integrating in-context examples further improves the translation of dialectal expressions. Our work establishes a robust framework for goal-directed, inclusive dialect translation, providing both rigorous evaluation and critical insights into model performance.

翻译：标准语至方言的机器翻译仍面临挑战，主要源于大语言模型中持续存在的方言鸿沟，以及n元语法指标固有的评估失真问题——这类指标更倾向于复制源语言而非实现真实的方言翻译。本文提出方言优化（DIA-REFINE）框架，该框架通过翻译、验证与反馈的迭代循环，借助外部方言分类器的反馈机制，引导大语言模型生成忠实的目标方言输出。为克服基于n元语法指标的局限性，我们引入了方言保真度分数（DFS）以量化语言偏移程度，以及目标方言比例（TDR）以衡量方言翻译的成功率。在韩语方言上进行的实验涵盖了零样本学习和上下文学习基线，结果表明DIA-REFINE能持续提升方言保真度。所提出的指标能够区分两类情况：一是“虚假成功”案例，即高n元语法分数掩盖了方言翻译的失败；二是“真实尝试”案例，即真正的方言翻译尝试却获得低n元语法分数。我们还观察到，不同模型对该框架的响应程度存在差异，且整合上下文示例能进一步提升方言表达的翻译质量。本研究为面向目标的包容性方言翻译建立了一个稳健的框架，既提供了严谨的评估方法，也揭示了模型性能的关键洞见。