Model Compression Shared Task @ WMT 2026 - Second (Last) Call for Participation

Dear all,

Apologies for cross-posting. We are pleased to announce the second call of
the Model Compression Shared Task
<https://www2.statmt.org/wmt26/model-compression.html> at WMT 2026
<https://www2.statmt.org/wmt26/>.

This shared task aims to evaluate the potential of model compression
techniques in reducing the size of general-purpose large language models,
with the goal of achieving an optimal balance between practical
deployability and high translation quality in specific machine translation
(MT) scenarios. The task’s broader objectives include fostering research
into the efficient, accessible, and sustainable deployment of LLMs for MT,
establishing a common evaluation framework to monitor progress in model
compression across a wide range of languages, and enabling meaningful
comparisons with state-of-the-art MT systems through standardized
evaluation protocols designed to assess not only translation quality but
also computational efficiency.

Although the focus is on model compression, the task is closely aligned
with the General MT shared task
<https://www2.statmt.org/wmt26/translation-task.html>, sharing test data
from a subset of its language directions, as well as protocols for
automatic MT quality evaluation. Additionally, the task follows the same
timeline as the flagship WMT task.

We warmly invite participation from academic teams and industry players
interested in applying existing compression methods to MT or exploring
innovative, cutting-edge approaches.

THE TASK IN A NUTSHELL

Goal: Reduce the size of a general-purpose LLM while maintaining a balance
between model compactness and MT performance.

Languages: The second round of the task will focus on a subset of the
languages covered by the General MT task, namely: Czech to German, English
to Chinese (Simplified), and English to Arabic (Egyptian).

Conditions:

   -

   Constrained: Participants will compress a specific model, using a
   predefined pool of data for calibration and fine-tuning (if needed) to
   ensure directly comparable results.
   -

   Unconstrained: Participants are free to compress any model, provided its
   original size is below 20B parameters, and use any additional data for
   calibration and fine-tuning.


Participation format: Participants will share their compressed models to be
run on a standardized hardware environment provided by the organizers.

Evaluation Criteria:

   -

   Translation quality: Automatically assessed using multiple metrics, e.g.
   Comet, MetricX, and an LLM-as-a-judge framework.
   -

   Model size: Defined by memory usage.
   -

   Inference speed: Measured by total processing time over the test set.


IMPORTANT DATES

   -

   Test data and submission information has just been released
   -

   Model Submission deadline: July 2, 2026
   -

   System description paper submission: in line with WMT26
   <https://www2.statmt.org/wmt26/index.html>
   -

   Camera-ready submission: in line with WMT26
   <https://www2.statmt.org/wmt26/index.html>
   -

   WMT 2026 Conference (co-located with EMNLP2026 <https://2026.emnlp.org/>
   in Budapest, Hungary): November, 2026


WEBSITE:  https://www2.statmt.org/wmt26/model-compression.html

ORGANIZERS:

Marco Gaido, Fondazione Bruno Kessler

Matteo Negri, Fondazione Bruno Kessler

Roman Grundkiewicz - Microsoft Translator

TG Gowda - Microsoft Translator

CONTACTS:

Marco Gaido - [email protected]

Matteo Negri - [email protected]

-- 
--
Le informazioni contenute nella presente comunicazione sono di natura 
privata e come tali sono da considerarsi riservate ed indirizzate 
esclusivamente ai destinatari indicati e per le finalità strettamente 
legate al relativo contenuto. Se avete ricevuto questo messaggio per 
errore, vi preghiamo di eliminarlo e di inviare una comunicazione 
all’indirizzo e-mail del mittente.

--
The information transmitted is 
intended only for the person or entity to which it is addressed and may 
contain confidential and/or privileged material. If you received this in 
error, please contact the sender and delete the material.

_______________________________________________
Corpora mailing list -- [email protected]
https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/
To unsubscribe send an email to [email protected]