arXiv cs.CL· Aleix Sant, Jordi Luque, Carlos Escolano·· 13 小时前AI 评分29
面向 WMT 2026 MIST 开放式问答的保任务多语言指令微调
Task-Preserving Multilingual Instruction Tuning for Open-Ended QA in WMT 2026 MIST
AI 导读
研究团队用 LoRA 将 Qwen3-8B 适配到 WMT 2026 多语言指令共享任务，数据为组织方提供的 EuroAlpaca 与跨语言增强版 CrossEuroAlpaca，覆盖十种任务语言。
正文 · 原文
Abstract:This paper describes our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation, and CrossEuroAlpaca, a cross-lingual augmentation that assigns different source and target languages to instructions, contexts and responses. Our system targets open-ended question answering (QA-OEG) in ten shared-task languages represented in the auxiliary data. Under matched decoding, adaptation improves the mean Gemma-4 judge score on target-language QA-OEG by 7.8% relative to the base model. On an additional evaluation using the Aya Evaluation Suite across all shared-task languages, it yields relative gains of 41.5% in macro-averaged ROUGE-L and 2.9% in BERTScore-F1, with larger improvements in target languages. However, these gains are task- and language-specific. Gemma-4 scores improve for QA-OEG and summarisation in the target languages but decline for context-grounded QA there and across all three tasks in the non-target languages.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.29926 [cs.CL] |
| (or arXiv:2610.29926v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29926 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aleix Sant Savall [view email]
[v1]
Wed, 21 Oct 2026 16:02:34 UTC (33 KB)
来源：arXiv cs.CL · arxiv.org