@InProceedings{hrabal-bojar:2026:wmt,
  author    = {Hrabal, Miroslav  and  Bojar, Ondřej},
  title     = {CUNI at the WMT26 Automated MT Evaluation Shared Task},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1659--1664},
  abstract  = {We describe the CUNI submissions to the WMT26 Automated MT Evaluation Shared Task. We take part in error-span prediction (Task~1) and segment-level quality score prediction (Task~2). Our systems use a single open-weight Gemma 4 31B instruction-tuned model as a backbone. For Task~1, we decompose error prediction into semantic error detection, self-review, and a separate span-alignment step that maps free-form error descriptions to source and target character spans. We submit two variants of this approach, one additionally predicting MQM-style error categories. For Task~2, we explore two complementary approaches: regression over features extracted from the Task~1 predictions and LLM-based direct assessment on a 0--100 scale.},
  url       = {https://aclanthology.org/2026.wmt-1.98}
}