Generating Difficult-to-Translate Texts

Vilém Zouhar, Wenda Xu, Parker Riley, Juraj Juraska, Mara Finkelstein, Markus Freitag, Daniel Deutsch


Abstract
Machine translation benchmarks sourced from the real world are quickly obsoleted, due to most examples being easy for state-of-the-art translation models. This limits the benchmark’s ability to distinguish which model is better or to reveal models’ weaknesses. Current methods for creating difficult test cases, such as subsampling or from-scratch synthesis, either fall short of identifying difficult examples or suffer from a lack of diversity and naturalness. Inspired by the iterative process of human experts probing for model failures, we propose MT-breaker, a method where a large language model iteratively refines a source text to increase its translation difficulty. The LLM iteratively queries a target machine translation model to guide its generation of difficult examples. Our approach generates examples that are more challenging for the target MT model while preserving the diversity of natural texts. While the examples are tailored to a particular machine translation model during the generation, the difficulty also transfers to other models and languages.
Anthology ID:
2026.mme-main.14
Volume:
Proceedings of the First Workshop on Multilingual Multicultural Evaluation
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Pinzhen Chen, Vilém Zouhar, Hanxu Hu, Simran Khanuja, Wenhao Zhu, Barry Haddow, Alexandra Birch, Alham Fikri Aji, Rico Sennrich, Sara Hooker
Venues:
MME | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
204–219
Language:
URL:
https://aclanthology.org/2026.mme-main.14/
DOI:
Bibkey:
Cite (ACL):
Vilém Zouhar, Wenda Xu, Parker Riley, Juraj Juraska, Mara Finkelstein, Markus Freitag, and Daniel Deutsch. 2026. Generating Difficult-to-Translate Texts. In Proceedings of the First Workshop on Multilingual Multicultural Evaluation, pages 204–219, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Generating Difficult-to-Translate Texts (Zouhar et al., MME 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.mme-main.14.pdf