Tan, David; Chen, Pinzhen; van Genabith, Josef; Dutta Chowdhury, Koel
When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation
Demberg, Vera; Inui, Kentaro; Marquez, Lluís (Ed.): Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, pp. 345-358, Rabat, Morocco, 2026, ISBN 979-8-89176-381-4.
Large language models (LLMs) can be benchmark-contaminated, resulting in inflated scores that mask memorization as generalization, and in multilingual settings, this memorization can even transfer to „uncontaminated“ languages. Using the FLORES-200 translation benchmark as a diagnostic, we study two 7-8B instruction-tuned multilingual LLMs: Bloomz, which was trained on FLORES, and Llama as an uncontaminated control. We confirm Bloomz’s FLORES contamination and demonstrate that machine translation contamination can be cross-directional, artificially boosting performance in unseen translation directions due to target-side memorization. Further analysis shows that recall of memorized references often persists despite various source-side perturbation efforts like paraphrasing and named entity replacement. However, replacing named entities leads to a consistent decrease in BLEU, suggesting an effective probing method for memorization in contaminated models.