Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis

• URL: http://arxiv.org/abs/2412.05862v3
• Date: Thu, 01 May 2025 07:36:13 GMT
• Title: Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis
• Authors: Aman Kassahun Wassie, Mahdi Molaei, Yasmin Moslem,
• Abstract summary: We compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models.<n>Our experiments focus on the medical domain and cover four language directions with varied resource availability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on the medical domain and cover four language directions with varied resource availability: English-to-French, English-to-Portuguese, English-to-Swahili, and Swahili-to-English. Despite recent advancements, LLMs demonstrate a significant quality gap in specialized translation compared to multilingual encoder-decoder MT models such as NLLB-200. Our results indicate that NLLB-200 3.3B outperforms all evaluated LLMs in the 7-8B parameter range across three out of the four language directions. While fine-tuning improves the performance of LLMs such as Mistral and Llama, these models still underperform compared to fine-tuned NLLB-200 3.3B models. Our findings highlight the ongoing need for specialized MT models to achieve high-quality domain-specific translation, especially in medium-resource and low-resource settings. Moreover, the superior performance of larger LLMs over their 8B variants suggests potential value in pre-training domain-specific medium-sized language models, employing targeted data selection and knowledge distillation approaches to enhance both quality and efficiency in specialized translation tasks.

Related papers

• Enhancing Code Generation for Low-Resource Languages: No Silver Bullet [55.39571645315926]
  Large Language Models (LLMs) rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource languages, the limited availability of such data hampers the models' ability to generalize effectively. We present an empirical study investigating the effectiveness of several approaches for boosting LLMs' performance on low-resource languages.
  arXiv  Detail & Related papers  (2025-01-31T12:23:28Z)
• NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models [2.186901738997927]
  This paper introduces NusaMT-7B, an LLM-based machine translation model for low-resource Indonesian languages. Our approach integrates continued pre-training on monolingual data,Supervised Fine-Tuning (SFT), self-learning, and an LLM-based data cleaner to reduce noise in parallel sentences. Our results show that fine-tuned LLMs can enhance translation quality for low-resource languages, aiding in linguistic preservation and cross-cultural communication.
  arXiv  Detail & Related papers  (2024-10-10T11:33:25Z)
• What do Large Language Models Need for Machine Translation Evaluation? [12.42394213466485]
  Large language models (LLMs) can achieve results comparable to fine-tuned multilingual pre-trained language models. This paper explores what translation information, such as the source, reference, translation errors and annotation guidelines, is needed for LLMs to evaluate machine translation quality.
  arXiv  Detail & Related papers  (2024-10-04T09:50:45Z)
• X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale [25.257770733168012]
  Large language models (LLMs) have achieved remarkable success across various NLP tasks with a focus on English due to English-centric pre-training and limited multilingual data. We introduce **X-ALMA**, a model designed to ensure top-tier performance across 50 diverse languages.
  arXiv  Detail & Related papers  (2024-10-04T03:17:27Z)
• Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM [32.9914093870763]
  We introduce Mufu, which includes a selection of automatically generated multilingual candidates and an instruction to correct inaccurate translations in the prompt. Mufu prompts turn a translation task into a postediting one. Our experiments on En-XX translations over the Flores-200 dataset show LLMs finetuned against Mufu-style prompts are robust to poor quality auxiliary translation candidates.
  arXiv  Detail & Related papers  (2024-09-20T23:48:47Z)
• How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes [2.0109318570325847]
  We investigate the impact of fine-tuning the Llama 3 model using TMs from a specific organisation in the software sector. We fine-tune separate models for each training set and evaluate their performance based on automatic metrics, BLEU, chrF++, TER, and COMET. Our findings reveal improvement in translation performance with larger datasets across all metrics.
  arXiv  Detail & Related papers  (2024-09-05T12:06:38Z)
• Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation [62.202893186343935]
  We explore what it would take to adapt Large Language Models for low-resource languages. We show that parallel data is critical during both pre-training andSupervised Fine-Tuning (SFT) Our experiments with three LLMs across two low-resourced language groups reveal consistent trends, underscoring the generalizability of our findings.
  arXiv  Detail & Related papers  (2024-08-23T00:59:38Z)
• Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages [2.53740603524637]
  Machine translation models (MT) produce excellent multilingual representations, resulting in strong translation performance even for low-resource languages. In this work, we get the best both worlds by integrating MT encoders directly into language backbones via sample-efficient self-distillation. The resulting MT-LLMs preserve the inherent multilingual representational alignment from the MT encoder, allowing lower-resource languages to tap into the rich knowledge embedded in English-centric LLMs.
  arXiv  Detail & Related papers  (2024-06-18T16:00:20Z)
• Tele-FLM Technical Report [96.19923831660266]
  We introduce Tele-FLM (aka FLM-2), a 52B open-sourced multilingual large language model. It features a stable, efficient pre-training paradigm and enhanced factual judgment capabilities. It is comparable to strong open-sourced models that involve larger pre-training FLOPs, such as Llama2-70B and DeepSeek-67B.
  arXiv  Detail & Related papers  (2024-04-25T14:34:47Z)
• Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language [1.1702440973773898]
  This study explores the use of large language models for translating English into Mambai, a low-resource Austronesian language spoken in Timor-Leste. Our methodology involves the strategic selection of parallel sentences and dictionary entries for prompting. We find that including dictionary entries in prompts and a mix of sentences retrieved through-IDF and semantic embeddings significantly improves translation quality.
  arXiv  Detail & Related papers  (2024-04-07T05:04:38Z)
• adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds [2.648836772989769]
  adaptMLLM is an open-source tool for fine-tuning Multilingual Language Models (MLLMs) for Machine Translation (MT) It offers a range of metrics for model evaluation and the capability to deploy models as a translation service directly within the application. The adaptMLLM system demonstrated significant improvements compared with baselines from the LoResMT 2021 Shared Task.
  arXiv  Detail & Related papers  (2024-03-04T14:49:18Z)
• MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models [7.321459642283822]
  Finetuning can improve the performance of language models without requiring massive resources and compute. We finetune LLama-2-7B and Mistral-7B models on two synthetic multilingual instruction tuning datasets to determine its effect on model performance. We find that PEFT of smaller open-source models sometimes bridges the gap between the performance of these models and the larger ones, however, English performance can take a hit.
  arXiv  Detail & Related papers  (2024-01-15T11:06:43Z)
• Adapting Large Language Models for Document-Level Machine Translation [46.370862171452444]
  Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs.
  arXiv  Detail & Related papers  (2024-01-12T09:29:13Z)
• SCALE: Synergized Collaboration of Asymmetric Language Translation Engines [105.8983433641208]
  We introduce a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one unified translation engine. By introducing translation from STM into the triplet in-context demonstrations, SCALE unlocks refinement and pivoting ability of LLM. Our experiments show that SCALE significantly outperforms both few-shot LLMs (GPT-4) and specialized models (NLLB) in challenging low-resource settings.
  arXiv  Detail & Related papers  (2023-09-29T08:46:38Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis [103.89753784762445]
  Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT) This paper systematically investigates the advantages and challenges of LLMs for MMT. We thoroughly evaluate eight popular LLMs, including ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2023-04-10T15:51:30Z)
• Examining Scaling and Transfer of Language Model Architectures for Machine Translation [51.69212730675345]
  Language models (LMs) process sequences in a single stack of layers, and encoder-decoder models (EncDec) utilize separate layer stacks for input and output processing. In machine translation, EncDec has long been the favoured approach, but with few studies investigating the performance of LMs.
  arXiv  Detail & Related papers  (2022-02-01T16:20:15Z)

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.