Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety

[Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety](https://aclanthology.org/2026.eamt-1.23.pdf)

[Paolo Di Natale](/people/paolo-di-natale/unverified/),
[Elena Chiocchetti](/people/elena-chiocchetti/unverified/),
[Marlies Alber](/people/marlies-alber/unverified/),
[Egon W. Stemle](/people/egon-stemle/)

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.- Anthology ID:

- 2026.eamt-1.23
- Volume:
[Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)](/volumes/2026.eamt-1/)- Month:

• June
• Year:
• 2026
• Address:
• Tilburg, The Netherlands
• Editors: Dimitar Shterionov,Eva Vanmassenhove,Mirella De Sisto,Fred Blain,Javad Pourmostafa Roshan Sharami,Lisa Lepp,Chiara Manna,Argentina Anna Rescigno,Alina Karakanta,Ayla Rigouts Terryn,Manuel Lardelli,Natalia Resende,Elena Murgolo,Janiça Hackenbuchner,Anna Zaretskaya,Miquel Esplà-Gomis,Thierry Etchegoyhen,Dagmar Gromann,Rachel Bawden,Barry Haddow,Sara Szoc,Mikel Forcada,Helena Moniz- Venue:

[EAMT](/venues/eamt/)- SIG:
- Publisher:

• European Association for Machine Translation

- Note:
- Pages:

• 348–371

- Language:
- URL:
[https://aclanthology.org/2026.eamt-1.23/](https://aclanthology.org/2026.eamt-1.23/)- DOI:
- Cite (ACL):

• Paolo Di Natale, Elena Chiocchetti, Marlies Alber, and Egon W. Stemle. 2026. Beyond Simple Term Injection: Reasoning Models for Legal Translation in a Non-Dominant Language Variety. InProceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 348–371, Tilburg, The Netherlands. European Association for Machine Translation. - Cite (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)- PDF:
[https://aclanthology.org/2026.eamt-1.23.pdf](https://aclanthology.org/2026.eamt-1.23.pdf)