mlsanityData to 7 Oct 2026

Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs

arXiv 2505.22293 ↗First posted 28 May 2025cs.CLcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation, sometimes even outperforming traditional neural systems. However, previous research has highlighted the challenges of using LLMs, particularly with prompt engineering, for low-resource languages. In this work, we introduce Fragment-Shot Prompting, a novel in-context learning method that segments input and retrieves translation examples based on syntactic coverage, along with Pivoted Fragment-Shot, an extension that enables translation without direct parallel data. We evaluate these methods using GPT-3.5, GPT-4o, o1-mini, LLaMA-3.3, and DeepSeek-R1 for translation between Italian and two Ladin variants, revealing three key findings: (1) Fragment-Shot Prompting is effective for translating into and between the studied low-resource languages, with syntactic coverage positively correlating with translation quality; (2) Models with stronger reasoning abilities make more effective use of retrieved knowledge, generally produce better translations, and enable Pivoted Fragment-Shot to significantly improve translation quality between the Ladin variants; and (3) prompt engineering offers limited, if any, improvements when translating from a low-resource to a high-resource language, where zero-shot prompting already yields satisfactory results. We publicly release our code and the retrieval corpora.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 31 of its 40 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

31 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  6. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  7. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  8. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 533
  9. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  10. 2023Low-Resource Languages Jailbreak GPT-4cited by 290
  11. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  12. 2022In-context Examples Selection for Machine Translationcited by 172
18 more
  1. 2024Do Large Language Models Latently Perform Multi-Hop Reasoning?cited by 165
  2. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  3. 2022BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Promptingcited by 90
  4. 2024LLMs Are Few-Shot In-Context Low-Resource Language Learnerscited by 68
  5. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  6. 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOMcited by 58
  7. 2023Steering Large Language Models for Machine Translation with Finetuning and In-Context Learningcited by 48
  8. 2023How to Design Translation Prompts for ChatGPT: An Empirical Studycited by 31
  9. 2024Teaching Large Language Models an Unseen Language on the Flycited by 29
  10. 2024Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?cited by 23
  11. 2024The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilitiescited by 22
  12. 2024Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problemcited by 17
  13. 2024How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizescited by 17
  14. 2024Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?cited by 16
  15. 2024Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Languagecited by 12
  16. 2024Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translationcited by 12
  17. 2024An Empirical Study of In-context Learning in LLMs for Machine Translationcited by 9
  18. 2024Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladincited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Modelscited by 1
  2. 2026A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024What do Large Language Models Need for Machine Translation Evaluation?
  2. 2026Reasoning about In-Context Samples for Machine-Translation
  3. 2022Bootstrapping Multilingual Semantic Parsers using Large Language Models
  4. 2024Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
  5. 2024Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches
  6. 2024Learning-From-Mistakes Prompting for Indigenous Language Translation
  7. 2025How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting
  8. 2024Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM