Improving Low-Resource Translation with Dictionary-Guided Fine-Tuning and RL: A Spanish-to-Wayuunaiki Study

• URL: http://arxiv.org/abs/2508.19481v1
• Date: Tue, 26 Aug 2025 23:50:55 GMT
• Title: Improving Low-Resource Translation with Dictionary-Guided Fine-Tuning and RL: A Spanish-to-Wayuunaiki Study
• Authors: Manuel Mosquera, Melissa Robles, Johan Rodriguez, Ruben Manrique,
• Abstract summary: We propose a novel approach that enhances translation for low-resource languages by integrating an external dictionary tool and training models end-to-end.<n>We frame translation as a tool-augmented decision-making problem in which the model can selectively consult a bilingual dictionary during generation.<n>Preliminary results show that our tool-augmented models achieve up to +3.37 BLEU improvement over previous work.
• Score: 0.27998963147546146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Low-resource machine translation remains a significant challenge for large language models (LLMs), which often lack exposure to these languages during pretraining and have limited parallel data for fine-tuning. We propose a novel approach that enhances translation for low-resource languages by integrating an external dictionary tool and training models end-to-end using reinforcement learning, in addition to supervised fine-tuning. Focusing on the Spanish-Wayuunaiki language pair, we frame translation as a tool-augmented decision-making problem in which the model can selectively consult a bilingual dictionary during generation. Our method combines supervised instruction tuning with Guided Reward Policy Optimization (GRPO), enabling the model to learn both when and how to use the tool effectively. BLEU similarity scores are used as rewards to guide this learning process. Preliminary results show that our tool-augmented models achieve up to +3.37 BLEU improvement over previous work, and a 18% relative gain compared to a supervised baseline without dictionary access, on the Spanish-Wayuunaiki test set from the AmericasNLP 2025 Shared Task. We also conduct ablation studies to assess the effects of model architecture and training strategy, comparing Qwen2.5-0.5B-Instruct with other models such as LLaMA and a prior NLLB-based system. These findings highlight the promise of combining LLMs with external tools and the role of reinforcement learning in improving translation quality in low-resource language settings.

Related papers

• Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning [0.36398711296758063]
  We investigate a self-supervised reinforcement-learning-based fine-tuning for translation in low-resource settings.<n>Our approach translates English into a target low-resource language and then back into English, using a combination of chrF++ and BLEU.<n>We observe consistent improvements for the following languages: Central Aymara, Friulian, Wolof and Russian.
  arXiv  Detail & Related papers  (2026-01-18T18:44:49Z)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs [54.59207567677249]
  Large language models (LLMs) still struggle across tasks outside of high-resource languages.<n>In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce.
  arXiv  Detail & Related papers  (2025-05-23T20:28:31Z)
• Improving Multilingual Language Models by Aligning Representations through Steering [10.159957091670883]
  This paper investigates how Large Language Models (LLMs) represent non-English tokens.<n>We propose a lightweight intervention method using representation steering, where a learned vector is added to the residual stream at a single model layer to enhance multilingual performance.
  arXiv  Detail & Related papers  (2025-05-19T00:14:43Z)
• QueEn: A Large Language Model for Quechua-English Translation [20.377876059048692]
  We propose QueEn, a novel approach for Quechua-English translation that combines Retrieval-Augmented Generation (RAG) with parameter-efficient fine-tuning techniques.<n>Our approach substantially exceeds baseline models, with a BLEU score of 17.6 compared to 1.5 for standard GPT models.
  arXiv  Detail & Related papers  (2024-12-06T17:04:21Z)
• Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey [52.00674453604779]
  This survey organizes the literature on the design and optimization of emerging structures around post-trained LMs.<n>We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step processes with tools.
  arXiv  Detail & Related papers  (2024-10-21T18:06:25Z)
• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking [1.3716808114696444]
  Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations.
  arXiv  Detail & Related papers  (2024-05-07T21:58:45Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• A Novel Paradigm Boosting Translation Capabilities of Large Language Models [11.537249547487045]
  The paper proposes a novel paradigm consisting of three stages: Secondary Pre-training using Extensive Monolingual Data, Continual Pre-training with Interlinear Text Format Documents, and Leveraging Source-Language Consistent Instruction for Supervised Fine-Tuning. Experimental results conducted using the Llama2 model, particularly on Chinese-Llama2, demonstrate the improved translation capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-03-18T02:53:49Z)
• Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? [82.02076369811402]
  Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. We present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements.
  arXiv  Detail & Related papers  (2024-03-04T10:48:13Z)
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation [127.81351683335143]
  Cross-lingual pretraining requires models to align the lexical- and high-level representations of the two languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language model pretraining with lexical-level information by using type-level cross-lingual subword embeddings.
  arXiv  Detail & Related papers  (2021-03-18T21:17:58Z)
• Mixed-Lingual Pre-training for Cross-lingual Summarization [54.4823498438831]
  Cross-lingual Summarization aims at producing a summary in the target language for an article in the source language. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks like translation and monolingual tasks like masked language models. Our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results.
  arXiv  Detail & Related papers  (2020-10-18T00:21:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.