@inproceedings{di-natale-etal-2026-beyond,
title = "Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety",
author = "Di Natale, Paolo and
Chiocchetti, Elena and
Alber, Marlies and
Stemle, Egon W.",
editor = "Shterionov, Dimitar and
Vanmassenhove, Eva and
De Sisto, Mirella and
Blain, Fred and
Pourmostafa Roshan Sharami, Javad and
Lepp, Lisa and
Manna, Chiara and
Rescigno, Argentina Anna and
Karakanta, Alina and
Rigouts Terryn, Ayla and
Lardelli, Manuel and
Resende, Natalia and
Murgolo, Elena and
Hackenbuchner, Jani{\c{c}}a and
Zaretskaya, Anna and
Espl{\`a}-Gomis, Miquel and
Etchegoyhen, Thierry and
Gromann, Dagmar and
Bawden, Rachel and
Haddow, Barry and
Szoc, Sara and
Forcada, Mikel and
Moniz, Helena",
booktitle = "Proceedings of the 26th Annual Conference of the {E}uropean Association for Machine Translation (Volume 1)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-1.23/",
pages = "348--371",
ISBN = "9789403901411",
abstract = "Term injection in machine translation is undergoing a paradigm shift in the era of large language models (LLMs). Although recent shared-task results suggest near-saturation for sentence-level term injection from pre-defined glossaries, it remains unclear whether this also holds in more challenging settings. We address this question with a custom test set for legal translation from Italian into South Tyrolean German, a non-dominant and under-resourced language variety. We cover three terminology challenges: simple term injection, localisation of abbreviated forms, and homonym disambiguation. We focus on Reasoning Models (RMs) leveraging Test-Time Scaling, comparing them with different architectures and contributing a human analysis of reasoning traces. We find that reasoning offers little benefit for simple term insertion, but yields clear gains for semantically complex cases such as homonym disambiguation. However, human evaluation of reasoning traces shows that these gains do not necessarily reflect robust and factually grounded translation-specific reasoning. We further show that without external terminological resources, even state-of-the-art RMs struggle to retrieve correct terminology for a non-dominant variety, while NMT small models remain competitive when trained on in-domain bilingual corpora. Based on these findings, we propose data collection strategies for inducing translation-specific reasoning, frameworks for adapting to and evaluating terminology across many language varieties, and terminology challenges beyond simple term injection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-natale-etal-2026-beyond">
<titleInfo>
<title>Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Di Natale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Chiocchetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marlies</namePart>
<namePart type="family">Alber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Egon</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Stemle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">De Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Lepp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Argentina</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Rescigno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="family">Rigouts Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Lardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Resende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiça</namePart>
<namePart type="family">Hackenbuchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tilburg, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">9789403901411</identifier>
</relatedItem>
<abstract>Term injection in machine translation is undergoing a paradigm shift in the era of large language models (LLMs). Although recent shared-task results suggest near-saturation for sentence-level term injection from pre-defined glossaries, it remains unclear whether this also holds in more challenging settings. We address this question with a custom test set for legal translation from Italian into South Tyrolean German, a non-dominant and under-resourced language variety. We cover three terminology challenges: simple term injection, localisation of abbreviated forms, and homonym disambiguation. We focus on Reasoning Models (RMs) leveraging Test-Time Scaling, comparing them with different architectures and contributing a human analysis of reasoning traces. We find that reasoning offers little benefit for simple term insertion, but yields clear gains for semantically complex cases such as homonym disambiguation. However, human evaluation of reasoning traces shows that these gains do not necessarily reflect robust and factually grounded translation-specific reasoning. We further show that without external terminological resources, even state-of-the-art RMs struggle to retrieve correct terminology for a non-dominant variety, while NMT small models remain competitive when trained on in-domain bilingual corpora. Based on these findings, we propose data collection strategies for inducing translation-specific reasoning, frameworks for adapting to and evaluating terminology across many language varieties, and terminology challenges beyond simple term injection.</abstract>
<identifier type="citekey">di-natale-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.23/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>348</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety
%A Di Natale, Paolo
%A Chiocchetti, Elena
%A Alber, Marlies
%A Stemle, Egon W.
%Y Shterionov, Dimitar
%Y Vanmassenhove, Eva
%Y De Sisto, Mirella
%Y Blain, Fred
%Y Pourmostafa Roshan Sharami, Javad
%Y Lepp, Lisa
%Y Manna, Chiara
%Y Rescigno, Argentina Anna
%Y Karakanta, Alina
%Y Rigouts Terryn, Ayla
%Y Lardelli, Manuel
%Y Resende, Natalia
%Y Murgolo, Elena
%Y Hackenbuchner, Janiça
%Y Zaretskaya, Anna
%Y Esplà-Gomis, Miquel
%Y Etchegoyhen, Thierry
%Y Gromann, Dagmar
%Y Bawden, Rachel
%Y Haddow, Barry
%Y Szoc, Sara
%Y Forcada, Mikel
%Y Moniz, Helena
%S Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901411
%F di-natale-etal-2026-beyond
%X Term injection in machine translation is undergoing a paradigm shift in the era of large language models (LLMs). Although recent shared-task results suggest near-saturation for sentence-level term injection from pre-defined glossaries, it remains unclear whether this also holds in more challenging settings. We address this question with a custom test set for legal translation from Italian into South Tyrolean German, a non-dominant and under-resourced language variety. We cover three terminology challenges: simple term injection, localisation of abbreviated forms, and homonym disambiguation. We focus on Reasoning Models (RMs) leveraging Test-Time Scaling, comparing them with different architectures and contributing a human analysis of reasoning traces. We find that reasoning offers little benefit for simple term insertion, but yields clear gains for semantically complex cases such as homonym disambiguation. However, human evaluation of reasoning traces shows that these gains do not necessarily reflect robust and factually grounded translation-specific reasoning. We further show that without external terminological resources, even state-of-the-art RMs struggle to retrieve correct terminology for a non-dominant variety, while NMT small models remain competitive when trained on in-domain bilingual corpora. Based on these findings, we propose data collection strategies for inducing translation-specific reasoning, frameworks for adapting to and evaluating terminology across many language varieties, and terminology challenges beyond simple term injection.
%U https://aclanthology.org/2026.eamt-1.23/
%P 348-371
Markdown (Informal)
[Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety](https://aclanthology.org/2026.eamt-1.23/) (Di Natale et al., EAMT 2026)
ACL