CUNI at WMT25 General Translation Task

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511588" target="_blank" >RIV/00216208:11320/25:10511588 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2025.wmt-1.44/" target="_blank" >https://aclanthology.org/2025.wmt-1.44/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

CUNI at WMT25 General Translation Task

Original language description

This paper describes the CUNI submissions to the WMT25 General Translation task, namely for the English to Czech, English to Serbian, Czech to German and Czech to Ukrainian language pairs. We worked in multiple teams, each with a different approach, spanning from traditional, smaller Transformer NMT models trained on both sentence and document level, to fine-tuning LLMs using LoRA and CPO. We show that these methods are effective in improving automatic MT evaluation scores compared to the base pretrained models.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Tenth Conference on Machine Translation

ISBN

979-8-89176-341-8

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

680-687

Publisher name

Association for Computational Linguistics

Place of publication

Kerrville, TX, USA

Event location

Suzhou, China

Event date

Nov 8, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—