Paper
Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
Authors
Aishwarya Ramasethu, Niyathi Allu, Rohin Garg, Harshwardhan Fartale, Dun Li Chan
Abstract
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.16660v1</id>\n <title>Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?</title>\n <updated>2026-03-17T15:28:46Z</updated>\n <link href='https://arxiv.org/abs/2603.16660v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.16660v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-17T15:28:46Z</published>\n <arxiv:comment>18 pages (9 main paper and 9 Appendix), 1 figure, 19 tables. Accepted at LoResMT 2026: EACL 2026 Workshop. OpenReview link: https://openreview.net/forum?id=mg0UfW2sdc#discussion</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Aishwarya Ramasethu</name>\n </author>\n <author>\n <name>Niyathi Allu</name>\n </author>\n <author>\n <name>Rohin Garg</name>\n </author>\n <author>\n <name>Harshwardhan Fartale</name>\n </author>\n <author>\n <name>Dun Li Chan</name>\n </author>\n </entry>"
}