{"ID":2865449,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22490","arxiv_id":"2509.22490","title":"JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA","abstract":"This paper presents the JGU Mainz submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: Machine Translation and Question Answering, focusing on Ukrainian, Upper Sorbian, and Lower Sorbian. For each language, we jointly fine-tune a Qwen2.5-3B-Instruct model for both tasks with parameter-efficient finetuning. Our pipeline integrates additional translation and multiple-choice question answering (QA) data. For Ukrainian QA, we further use retrieval-augmented generation. We also apply ensembling for QA in Upper and Lower Sorbian. Experiments show that our models outperform the baseline on both tasks.","short_abstract":"This paper presents the JGU Mainz submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: Machine Translation and Question Answering, focusing on Ukrainian, Upper Sorbian, and Lower Sorbian. For each language, we jointly fine-tune a Qwen2.5-3B-Instruct model for both tasks with paramete...","url_abs":"https://arxiv.org/abs/2509.22490","url_pdf":"https://arxiv.org/pdf/2509.22490v1","authors":"[\"Hossain Shaikh Saadi\",\"Minh Duc Bui\",\"Mario Sanz-Guerrero\",\"Katharina von der Wense\"]","published":"2025-09-26T15:35:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}