Year: 2025
Type: conference-paper
Abstract: 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 standardto-dialect translation task, also comparing with few-shot GPT-4o translation.In the absence of human annotators, we adopt a multimetric 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.
Authors: Roman Kyslyi, Yuliia Maksymiuk, Ihor Pysmennyi
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412944200