@InProceedings{diskin:2026:wmt,
  author    = {Diskin, Michael},
  title     = {One Model, Five Tasks, Two RTX 3090 GPUs: The HSE System for the Sorbian Track of WMT26 Multitask LLMs with Limited Resources},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {2651--2660},
  abstract  = {We describe HSE's submission to the Sorbian track of WMT26 Multitask LLMs with Lim- ited Resources, where a single 2B-parameter model must translate between German, Up- per Sorbian, and Lower Sorbian and also an- swer multiple-choice questions, check spelling and grammar, and solve maths problems in both Sorbian languages. Our system is one LoRA adapter on Qwen3.5-2B, trained on the official parallel data, synthetic spelling and grammar examples, a question-answering proxy, and English GSM8K in about nine GPU- hours on two consumer RTX 3090 GPUs. Ex- tended translation-only fine-tuning cost about ten points of question-answering accuracy, re- producing a WMT25 finding, and nearly erased the output conventions of the other tasks; the multitask mixture recovered them at almost no translation cost. The system ranked fourth of four teams. It far exceeded the baseline on translation (21.7 → 61.5 chrF++) and spell checking (6.7 → 63.6), but on grammar check- ing and maths reasoning it learned the answer format without the skill: the grammar score is almost exactly the share of error-free sentences, and maths accuracy did not exceed the baseline. Two negative results may transfer to other low- resource settings. Synthetic holdouts did not predict performance on the official tasks in ei- ther direction, and self-translated training prob- lems passed every automatic check yet changed meaning in at least 6 of 20 inspected cases. The model is publicly available.},
  url       = {https://aclanthology.org/2026.wmt-1.208}
}