# Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation

arXiv: https://arxiv.org/abs/2511.06680 · HTML: https://mlsanity.com/paper/2511.06680/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [LLMs Are Few-Shot In-Context Low-Resource Language Learners](https://mlsanity.com/paper/2403.16512/) (2024)
- [AraT5: Text-to-Text Transformers for Arabic Language Generation](https://mlsanity.com/paper/2109.12068/) (2021)
- [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024)
- [DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages](https://mlsanity.com/paper/2403.11009/) (2024)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [Quantifying the Dialect Gap and its Correlates Across Languages](https://mlsanity.com/paper/2310.15135/) (2023)
- [Dialect-robust Evaluation of Generated Text](https://mlsanity.com/paper/2211.00922/) (2022)
- [Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu](https://mlsanity.com/paper/2502.11862/) (2025)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography](https://mlsanity.com/paper/2311.16865/) (2023)
- [Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialects](https://mlsanity.com/paper/2406.19564/) (2024)
- [xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics](https://mlsanity.com/paper/2406.14553/) (2024)
- [Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification](https://mlsanity.com/paper/2403.05640/) (2024)
- [Ensembling Finetuned Language Models for Text Classification](https://mlsanity.com/paper/2410.19889/) (2024)
- [Jejueo Datasets for Machine Translation and Speech Synthesis](https://mlsanity.com/paper/1911.12071/) (2019)

## Built on by (most cited first, 2 of 2)

- [textitVersteasch du mi? Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language](https://mlsanity.com/paper/2603.28213/) (2026)
- [Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery](https://mlsanity.com/paper/2610.00164/) (2026)

## Abstract (arXiv)

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.