# Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation

arXiv: https://arxiv.org/abs/2506.07617 · HTML: https://mlsanity.com/paper/2506.07617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Quantifying the Dialect Gap and its Correlates Across Languages](https://mlsanity.com/paper/2310.15135/) (2023)
- ["It's how you do things that matters": Attending to Process to Better Serve Indigenous Communities with Language Technologies](https://mlsanity.com/paper/2402.02639/) (2024)
- [A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography](https://mlsanity.com/paper/2311.16865/) (2023)
- [From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation](https://mlsanity.com/paper/2404.09138/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs](https://mlsanity.com/paper/2512.14179/) (2025)

## Abstract (arXiv)

In this paper we introduce the first effort to adapt large language models (LLMs) to the Ukrainian dialect (in our case Hutsul), a low-resource and morphologically complex dialect spoken in the Carpathian Highlands. We created a parallel corpus of 9852 dialect-to-standard Ukrainian sentence pairs and a dictionary of 7320 dialectal word mappings. We also addressed data shortage by proposing an advanced Retrieval-Augmented Generation (RAG) pipeline to generate synthetic parallel translation pairs, expanding the corpus with 52142 examples. We have fine-tuned multiple open-source LLMs using LoRA and evaluated them on a standard-to-dialect translation task, also comparing with few-shot GPT-4o translation. In the absence of human annotators, we adopt a multi-metric evaluation strategy combining BLEU, chrF++, TER, and LLM-based judgment (GPT-4o). The results show that even small(7B) finetuned models outperform zero-shot baselines such as GPT-4o across both automatic and LLM-evaluated metrics. All data, models, and code are publicly released at: https://github.com/woters/vuyko-hutsul