TUM-Heilbronn: WMT26 Multilingual Instruction Shared Task

Abstract

This paper describes the TUM-Heilbronn sys-tem submission to the WMT26 Multilingual Instruction Shared Task (MIST). The MIST covers three tasks: context-based question answering, open-ended generation, and cross-lingual summarization to evaluate the multi-lingual instruction-following ability of large language models. We fine-tune Qwen3.5-9B-Instruct on 27 diverse languages, across 10 different writing scripts. Our model outperformed 6 of the 15 models submitted to this shared task. Moreover, we ranked first in truthfulness (i.e., decline to answer when the context lacks sufficient information) on the context-based question-answering task. Cross-lingual summarization remains a challenging task for all submitted models, with the lowest performance observed among the three tasks.