JGU Mainz’s Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA

Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina Von Der Wense


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.
Anthology ID:
2025.wmt-1.89
Volume:
Proceedings of the Tenth Conference on Machine Translation
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1151–1157
Language:
URL:
https://aclanthology.org/2025.wmt-1.89/
DOI:
Bibkey:
Cite (ACL):
Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, and Katharina Von Der Wense. 2025. JGU Mainz’s Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA. In Proceedings of the Tenth Conference on Machine Translation, pages 1151–1157, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
JGU Mainz’s Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA (Saadi et al., WMT 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.wmt-1.89.pdf