Newest papers

Task-Preserving Multilingual Instruction Tuning for Open-Ended QA in WMT 2026 MIST

Aleix Sant, Jordi Luque, Carlos Escolano · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29926 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

この文書は、WMT 2026 Multilingual Instruction Shared Taskへの提言を説明しています。我々は、Organizer が提供するデータ、ユーロアルパカ、タスク保存地帯化によって作成された多言語の指示データセット、およびクロスユーロアルパカ、指示、文脈および応答に異なるソース言語とターゲット言語を割り当てるクロス言語拡張に適応します。我々のシステムは、オープンエンド質問回答(QA-OEG)を支援データで表す10の共有タスク言語でターゲットします。カスタマイズされたデコードでは、適応はターゲット言語QA-OEGのGema-4審査の平均点数を基準モデルに比べて7.8%向上させます。

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Suite, Natural language processing, Artificial intelligence, Adaptation (eye), Training set

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange