Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test Sets

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511604" target="_blank" >RIV/00216208:11320/25:10511604 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2025.wmt-1.22/" target="_blank" >https://aclanthology.org/2025.wmt-1.22/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test Sets

Original language description

This paper presents the results of the General Machine Translation Task organized as part of the 2025 Conference on Machine Translation (WMT). Participants were invited to build systems for any of 30 language pairs. For half of these pairs, we conducted a human evaluation on test sets spanning four to five different domains.We evaluated 60 systems in total: 36 submitted by participants and 24 for which we collected translations from large language models (LLMs) and popular online translation providers.This year, we focused on creating challenging test sets by developing a difficulty sampling technique and using more complex source data. We evaluated system outputs with professional annotators using the Error Span Annotation (ESA) protocol, except for two language pairs, for which we used Multidimensional Quality Metrics (MQM) instead.We continued the trend of increasingly moving towards document-level translation, providing the source texts as whole documents containing multiple paragraphs.

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

59

Pages from-to

355-413

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

—