Improving LLMs for Machine Translation Using Synthetic Preference Data

• URL: http://arxiv.org/abs/2508.14951v1
• Date: Wed, 20 Aug 2025 14:24:16 GMT
• Title: Improving LLMs for Machine Translation Using Synthetic Preference Data
• Authors: Dario Vajda, Domen Vreš, Marko Robnik-Šikonja,
• Abstract summary: We explore how a general instruction can be improved for machine translation using relatively few easily produced data resources.<n>Using Slovene large language model, we improve GaMSBInstruct model using Preference Optimization (DPO)<n>We generated its training by translating English Wikipedia articles using two LLMs, GaMSBInstruct and EuroLLM-9BInstruct.<n>In comparison to the baseline model, the finetuned model achieved a COMET score gain of around 0.04 and 0.02, on translating Wikipedia articles.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models have emerged as effective machine translation systems. In this paper, we explore how a general instruction-tuned large language model can be improved for machine translation using relatively few easily produced data resources. Using Slovene as a use case, we improve the GaMS-9B-Instruct model using Direct Preference Optimization (DPO) training on a programmatically curated and enhanced subset of a public dataset. As DPO requires pairs of quality-ranked instances, we generated its training dataset by translating English Wikipedia articles using two LLMs, GaMS-9B-Instruct and EuroLLM-9B-Instruct. We ranked the resulting translations based on heuristics coupled with automatic evaluation metrics such as COMET. The evaluation shows that our fine-tuned model outperforms both models involved in the dataset generation. In comparison to the baseline models, the fine-tuned model achieved a COMET score gain of around 0.04 and 0.02, respectively, on translating Wikipedia articles. It also more consistently avoids language and formatting errors.

Related papers

• Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation [56.75665429851673]
  This paper introduces a novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment.<n>Experiments demonstrate that we can maintain or even improve model performance by compressing synthetic multimodal instructions by up to 90%.
  arXiv  Detail & Related papers  (2024-09-27T08:20:59Z)
• Strategies for Improving NL-to-FOL Translation with LLMs: Data Generation, Incremental Fine-Tuning, and Verification [9.36179617282876]
  We create a high-quality FOL-annotated subset of ProofWriter dataset using GPT-4o. Our results show state-of-the-art performance for ProofWriter and ProntoQA datasets using ProofFOL on LLaMA-2 and Mistral models.
  arXiv  Detail & Related papers  (2024-09-24T21:24:07Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)
• UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback [21.858896845159208]
  Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. Our method starts with an existing LLM and iteratively produces improved models by self-generating a large synthetic dataset.
  arXiv  Detail & Related papers  (2024-06-11T21:53:46Z)
• Context-Aware Machine Translation with Source Coreference Explanation [26.336947440529713]
  We propose a model that explains the decisions made for translation by predicting coreference features in the input. We evaluate our method in the WMT document-level translation task of English-German dataset, the English-Russian dataset, and the multilingual TED talk dataset.
  arXiv  Detail & Related papers  (2024-04-30T12:41:00Z)
• MLLM-DataEngine: An Iterative Refinement Approach for MLLM [62.30753425449056]
  We propose a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data. For quality, we resort to GPT-4 to generate high-quality data with each given data type.
  arXiv  Detail & Related papers  (2023-08-25T01:41:04Z)
• The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation [93.01964988474755]
  AutoMQM is a prompting technique which asks large language models to identify and categorize errors in translations. We study the impact of labeled data through in-context learning and finetuning. We then evaluate AutoMQM with PaLM-2 models, and we find that it improves performance compared to just prompting for scores.
  arXiv  Detail & Related papers  (2023-08-14T17:17:21Z)
• Better Datastore, Better Translation: Generating Datastores from Pre-Trained Models for Nearest Neural Machine Translation [48.58899349349702]
  Nearest Neighbor Machine Translation (kNNMT) is a simple and effective method of augmenting neural machine translation (NMT) with a token-level nearest neighbor retrieval mechanism. In this paper, we propose PRED, a framework that leverages Pre-trained models for Datastores in kNN-MT.
  arXiv  Detail & Related papers  (2022-12-17T08:34:20Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• Enhanced back-translation for low resource neural machine translation using self-training [0.0]
  This work proposes a self-training strategy where the output of the backward model is used to improve the model itself through the forward translation technique. The technique was shown to improve baseline low resource IWSLT'14 English-German and IWSLT'15 English-Vietnamese backward translation models by 11.06 and 1.5 BLEUs respectively. The synthetic data generated by the improved English-German backward model was used to train a forward model which out-performed another forward model trained using standard back-translation by 2.7 BLEU.
  arXiv  Detail & Related papers  (2020-06-04T14:19:52Z)

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.