用小模型同时做斯拉夫语翻译和问答，效果优于基线。
JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA
- 用参数高效微调联合训练小模型完成翻译与问答任务。
- 在乌克兰语问答上使用检索增强生成，提升准确率。
- 对波罗的语种采用集成策略，提升结果稳定性。
本文介绍马尔堡大学团队参加WMT25共享任务的成果，聚焦乌克兰语、上索布语和下索布语的机器翻译与问答任务。针对每种语言，我们采用参数高效微调方法，联合微调Qwen2.5-3B-Instruct模型以同时处理两项任务。该流程整合了额外的翻译数据和多项选择型问答数据。对于乌克兰语问答任务，进一步引入检索增强生成技术。此外，对上、下索布语的问答任务采用模型集成方法。实验表明，所提模型在两项任务上均优于基线系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。