@InProceedings{hou-temesgen-fraser:2026:wmt,
  author    = {Hou, Jen-Chien  and  Temesgen, Tsedeniya Kinfe  and  Fraser, Alexander},
  title     = {TUM-Heilbronn: WMT26 Multilingual Instruction Shared Task},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1932--1939},
  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 an- swering, 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 dif- ferent 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 sum- marization remains a challenging task for all submitted models, with the lowest performance observed among the three tasks.},
  url       = {https://aclanthology.org/2026.wmt-1.128}
}