@InProceedings{moerman-tezcan:2026:wmt,
  author    = {Moerman, Thomas  and  Tezcan, Arda},
  title     = {Getting More from Small LLMs and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian NLP},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {2667--2680},
  abstract  = {We describe LT3's submission to the WMT26 shared task on Multitask LLMs with Limited Resources for Upper Sorbian (hsb) and Lower Sorbian (dsb): one QLoRA-fine-tuned Qwen3.5-2B model serves machine translation, multiple-choice question answering, spell checking, grammar checking, and maths reasoning. Our approach centres on three components. First, retrieval augmentation: fuzzy-match (FM) exemplars, retrieved by character- and embedding-based similarity from authentic and back-translated sentence pools, are included in prompts at training and inference times. Second, synthetic task data: training data for spell- and grammar-checking is generated from dictionaries and monolingual text. Third, a scoring-based inference system: the model generates free text only for the open-ended tasks–translation and maths reasoning–while, for the other three tasks, it scores candidates from constrained spaces by ranking multiple-choice options in place and selecting spelling and grammar corrections from dictionary-derived candidates. Our primary system was the joint winner of the Sorbian track, ranking first or second across all five tasks and outperforming the next-best system by 7.7 accuracy points on question answering and 1.4 points on mathematical reasoning. These results show that, for low-resource languages, FM augmentation combined with back-translation can improve MT performance for a relatively small LLM, while inference-level strategies can further improve its performance on other tasks without compromising MT performance.},
  url       = {https://aclanthology.org/2026.wmt-1.210}
}