Multilingual Communication in the Asylum Context: Evaluating LLM-Based Machine Translation with Fuzzy Match Augmentation and Adaptive NMT across Resource Conditions under Low-Data Constraints

Thomas Moerman, Arda Tezcan, Lieve Macken


Abstract
Effective communication in asylum reception settings requires reliable machine translation (MT) across many languages, including low-resource ones. Using data from the ANON project, we compare retrieval-augmented LLM translation with adaptive Neural MT across 14 target languages with varying resource levels. Working with a very small translation memory of only 358 sentences, we evaluate fuzzy match (FM) augmentation as an in-context learning strategy for open-source and commercial LLMs and benchmark these against ModernMT with and without domain adaptation. In the LLM setting, FM-based example selection consistently outperforms random selection and zero-shot prompting, with the largest gains for low-resource languages. Adaptive NMT retains an overall advantage, although Gemini~Pro approaches its performance and outperforms it on 6 of 14 languages, highlighting a trade-off between translation quality and data sovereignty in privacy-sensitive contexts. These findings show that FM augmentation remains effective under severe data constraints and emphasise the importance of language-specific evaluation in multilingual MT.
Anthology ID:
2026.eamt-1.3
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 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
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
6–21
Language:
URL:
https://aclanthology.org/2026.eamt-1.3/
DOI:
Bibkey:
Cite (ACL):
Thomas Moerman, Arda Tezcan, and Lieve Macken. 2026. Multilingual Communication in the Asylum Context: Evaluating LLM-Based Machine Translation with Fuzzy Match Augmentation and Adaptive NMT across Resource Conditions under Low-Data Constraints. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 6–21, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
Multilingual Communication in the Asylum Context: Evaluating LLM-Based Machine Translation with Fuzzy Match Augmentation and Adaptive NMT across Resource Conditions under Low-Data Constraints (Moerman et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.3.pdf