3 papers
cs.CL2026
ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation
MichaÅ CiesióÅka, Dawid WiÅniewski, Adrian Charkiewicz +1
We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across 15 language pairs that preserves original layout metadata proposed for multim…
cs.CL2026
CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs
Kamil Guttmann, Zofia FraÅ, Artur Nowakowski +1
Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data privacy concerns. We demonstrate that smaller, open-source…
cs.CL2025
MultiSlav: Using Cross-Lingual Knowledge Transfer to Combat the Curse of Multilinguality
Artur Kot, MikoÅaj Koszowski, Wojciech Chojnowski +4
Does multilingual Neural Machine Translation (NMT) lead to The Curse of the Multlinguality or provides the Cross-lingual Knowledge Transfer within a language family? In this study,…