Comparing LLM-Based Translation Approaches for Extremely Low-Resource Languages

Jared Coleman, Ruben Rosales, Kira Toal, Diego Cuadros, Nicholas Leeds, Bhaskar Krishnamachari, Khalil Iskarous


Abstract
We present a comprehensive evaluation and extension of the LLM-Assisted Rule-Based Machine Translation (LLM-RBMT) paradigm, an approach that combines the strengths of rule-based methods and Large Language Models (LLMs) to support translation in no-resource settings. We present a robust new implementation (the Pipeline Translator) that generalizes the LLM-RBMT approach and enables flexible adaptation to novel constructions. We benchmark it against four alternatives (Builder, Instructions, RAG, and Fine-tuned translators) on a curated dataset of 150 English sentences, and compare them across translation quality and runtime. The Pipeline Translator consistently achieves the best overall performance. The LLM-RBMT methods (Pipeline and Builder) also offer an important advantage: they naturally align with evaluation strategies that prioritize grammaticality and semantic fidelity over surface-form overlap, which is critical for endangered languages where mistranslation carries high risk.
Anthology ID:
2026.loresmt-1.4
Volume:
Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Atul Kr. Ojha, Chao-hong Liu, Ekaterina Vylomova, Flammie Pirinen, Jonathan Washington, Nathaniel Oco, Xiaobing Zhao
Venues:
LoResMT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–68
Language:
URL:
https://aclanthology.org/2026.loresmt-1.4/
DOI:
Bibkey:
Cite (ACL):
Jared Coleman, Ruben Rosales, Kira Toal, Diego Cuadros, Nicholas Leeds, Bhaskar Krishnamachari, and Khalil Iskarous. 2026. Comparing LLM-Based Translation Approaches for Extremely Low-Resource Languages. In Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026), pages 49–68, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Comparing LLM-Based Translation Approaches for Extremely Low-Resource Languages (Coleman et al., LoResMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.loresmt-1.4.pdf