Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
This work addresses the challenge of machine translation for underrepresented languages in low-resource settings, but it is incremental as it builds on existing prompting techniques with limited gains.
The study tackled the problem of improving machine translation for low-resource languages using LLMs by investigating if linguistically related pivot languages and few-shot examples can guide on-the-fly adaptation without fine-tuning, finding that gains are modest and sensitive to example construction, with inconsistent results for well-represented languages.
Large Language Models (LLMs) have achieved strong performance across many downstream tasks, yet their effectiveness in extremely low-resource machine translation remains limited. Standard adaptation techniques typically rely on large-scale parallel data or extensive fine-tuning, which are infeasible for the long tail of underrepresented languages. In this work, we investigate a more constrained question: in data-scarce settings, to what extent can linguistically similar pivot languages and few-shot demonstrations provide useful guidance for on-the-fly adaptation in LLMs? We study a data-efficient experimental setup that combines linguistically related pivot languages with few-shot in-context examples, without any parameter updates, and evaluate translation behavior under controlled conditions. Our analysis shows that while pivot-based prompting can yield improvements in certain configurations, particularly in settings where the target language is less well represented in the model's vocabulary, the gains are often modest and sensitive to few shot example construction. For closely related or better represented varieties, we observe diminishing or inconsistent gains. Our findings provide empirical guidance on how and when inference-time prompting and pivot-based examples can be used as a lightweight alternative to fine-tuning in low-resource translation settings.