@inproceedings{mash-etal-2026-bsc,
title = "{BSC} Submission for {WMT}26 General Machine Translation Shared Task",
author = "Mash, Audrey and
Ayebakuro, Jonathan and
Bohman, Ella and
Liao, Xixian and
De Luca Fornaciari, Francesca and
Melero, Maite",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.72/",
pages = "1327--1343",
ISBN = "979-8-89176-474-3",
abstract = "We present the BSC submission to the WMT26 General Machine Translation shared task: a 7B decoder-only model covering 23 directions, adapted from the SALAMANDRA (Gonzalez-Agirre et al., 2025) family through vocabulary replacement, two rounds of continued pre-training (monolingual, followed by instruction-formatted parallel data), supervised fine-tuning on a translation-only instruction mixture, and preference optimisation applied selectively to six weak directions via CPO-SimPO (Xu et al., 2024; Meng et al., 2024) with LoRA adapters (Hu et al., 2021). Submissions are decoded with Minimum Bayes Risk selection over a candidate pool filtered for truncation, degeneracy and off-target script. As official human evaluation was unavailable at the time of writing, we report a stage-wise internal evaluation on FLORES+ and WMT24++, together with automatic scores for the submitted system on the 12 test-set directions for which references have been released. Instruction tuning accounts for almost all measurable gain, but its size differs by an order of magnitude between the two evaluation sets; preference optimisation moves automatic metrics by less than the drift among untreated directions. The model is released under a Research-Only Licence and is available on request."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mash-etal-2026-bsc">
<titleInfo>
<title>BSC Submission for WMT26 General Machine Translation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Audrey</namePart>
<namePart type="family">Mash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Ayebakuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ella</namePart>
<namePart type="family">Bohman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xixian</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">De Luca Fornaciari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>We present the BSC submission to the WMT26 General Machine Translation shared task: a 7B decoder-only model covering 23 directions, adapted from the SALAMANDRA (Gonzalez-Agirre et al., 2025) family through vocabulary replacement, two rounds of continued pre-training (monolingual, followed by instruction-formatted parallel data), supervised fine-tuning on a translation-only instruction mixture, and preference optimisation applied selectively to six weak directions via CPO-SimPO (Xu et al., 2024; Meng et al., 2024) with LoRA adapters (Hu et al., 2021). Submissions are decoded with Minimum Bayes Risk selection over a candidate pool filtered for truncation, degeneracy and off-target script. As official human evaluation was unavailable at the time of writing, we report a stage-wise internal evaluation on FLORES+ and WMT24++, together with automatic scores for the submitted system on the 12 test-set directions for which references have been released. Instruction tuning accounts for almost all measurable gain, but its size differs by an order of magnitude between the two evaluation sets; preference optimisation moves automatic metrics by less than the drift among untreated directions. The model is released under a Research-Only Licence and is available on request.</abstract>
<identifier type="citekey">mash-etal-2026-bsc</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.72/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1327</start>
<end>1343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BSC Submission for WMT26 General Machine Translation Shared Task
%A Mash, Audrey
%A Ayebakuro, Jonathan
%A Bohman, Ella
%A Liao, Xixian
%A De Luca Fornaciari, Francesca
%A Melero, Maite
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F mash-etal-2026-bsc
%X We present the BSC submission to the WMT26 General Machine Translation shared task: a 7B decoder-only model covering 23 directions, adapted from the SALAMANDRA (Gonzalez-Agirre et al., 2025) family through vocabulary replacement, two rounds of continued pre-training (monolingual, followed by instruction-formatted parallel data), supervised fine-tuning on a translation-only instruction mixture, and preference optimisation applied selectively to six weak directions via CPO-SimPO (Xu et al., 2024; Meng et al., 2024) with LoRA adapters (Hu et al., 2021). Submissions are decoded with Minimum Bayes Risk selection over a candidate pool filtered for truncation, degeneracy and off-target script. As official human evaluation was unavailable at the time of writing, we report a stage-wise internal evaluation on FLORES+ and WMT24++, together with automatic scores for the submitted system on the 12 test-set directions for which references have been released. Instruction tuning accounts for almost all measurable gain, but its size differs by an order of magnitude between the two evaluation sets; preference optimisation moves automatic metrics by less than the drift among untreated directions. The model is released under a Research-Only Licence and is available on request.
%U https://aclanthology.org/2026.wmt-main.72/
%P 1327-1343
Markdown (Informal)
[BSC Submission for WMT26 General Machine Translation Shared Task](https://aclanthology.org/2026.wmt-main.72/) (Mash et al., WMT 2026)
ACL
- Audrey Mash, Jonathan Ayebakuro, Ella Bohman, Xixian Liao, Francesca De Luca Fornaciari, and Maite Melero. 2026. BSC Submission for WMT26 General Machine Translation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1327–1343, Budapest, Hungary. Association for Computational Linguistics.