Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models

Miguel Angel Rios Gaona, Claudia Plieseis, Dragos Ciobanu, Alina Secara


Abstract
In-context learning is a method for improving machine translation in Large Language Models, but its performance is sensitive to the quality of the few-shot example selection. Current retrieval strategies use semantic similarity by computing sentence embeddings, and these methods often require significant computational overhead and specialised expertise. We evaluate the impact of retrieval strategies on translation performance in a specialised domain, comparing traditional, token-based fuzzy matching against semantic sentence embeddings. We use a medical corpus from the European Medicines Agency (EMEA) for the English-Romanian and English-German language pairs, and we evaluate translation quality with automatic metrics and manual evaluation. Our results show that 1-shot and 5-shot prompting significantly outperforms the 0-shot baselines for quality in automatic evaluations for both language pairs, and in manual evaluation for English-German. For the English-Romanian pair, the average scores of the manual evaluation for both quality and ranking follow the same trend, but with no statistical significance. Token-based fuzzy matching overwhelmingly has higher automatic quality scores than embedding-based retrieval.
Anthology ID:
2026.eamt-1.34
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:
538–550
Language:
URL:
https://aclanthology.org/2026.eamt-1.34/
DOI:
Bibkey:
Cite (ACL):
Miguel Angel Rios Gaona, Claudia Plieseis, Dragos Ciobanu, and Alina Secara. 2026. Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 538–550, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models (Gaona et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.34.pdf