Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition
Open access

Large-Language-Model-Enhanced Adaptive Optimization for Data-Limited Multi-Domain Machine Translation

Wei Yan
2026 · IEEE Access · Vol 14, pp. 120331-120348 · 0 citations · 43 references
Computer Science

TL;DR

DKA-LLM-MT is proposed, a large-language-model-enhanced adaptive optimization framework for data-limited multi-domain machine translation that provides an effective and reliable solution for domain-sensitive machine translation under limited bilingual supervision and offers practical support for bilingual reading, specialized translation assistance, and domain-oriented language learning.

Abstract

Data-limited multi-domain machine translation remains challenging because parallel corpora are scarce in specialized domains, domain terminology is highly constrained, and large language models may generate fluent but unfaithful translations. Direct prompting or ordinary fine-tuning is therefore insufficient for domain-sensitive translation scenarios. To address these issues, this paper proposes DKA-LLM-MT, a large-language-model-enhanced adaptive optimization framework for data-limited multi-domain machine translation. The framework follows a data–model–reliability design. First, a domain-knowledge-constrained data augmentation strategy generates pseudo-parallel corpora under terminology, semantic consistency, and domain-style constraints. Second, a retrieval-augmented parameter-efficient adaptation mechanism integrates domain memory retrieval, lightweight LoRA adapters, and dynamic domain routing. Third, a reliability-aware optimization mechanism incorporates semantic fidelity, terminology consistency, and hallucination risk into both training-time data selection and inference-time candidate reranking. Experiments are conducted on five public data-limited domain translation benchmarks covering medical, legal, technical, news, and spoken-style texts. The proposed method achieves an average BLEU of 36.18, chrF of 62.14, COMET of 0.816, and TER of 40.62, consistently outperforming strong neural, multilingual, and LLM-based baselines. Additional matched-backbone and same-language-pair analyses are included to separate the effect of domain adaptation from language-pair variation. Reliability evaluation further shows that DKA-LLM-MT improves terminology accuracy to 89.6% and reduces hallucination rate to 3.2%. The proposed framework provides an effective and reliable solution for domain-sensitive machine translation under limited bilingual supervision and offers practical support for bilingual reading, specialized translation assistance, and domain-oriented language learning.

DOI Semantic Scholar
Read PDF

Similar papers

Preprint Aug 2026

PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation

PAMT is proposed, a process-aligned training framework that combines cold-start domain-aware Long-CoT supervision with reinforcement learning that improves over base models, outperforms MT-specialized baselines on average, and remains competitive with strong LLMs/LRMs across in-domain, OOD, and multilingual settings.

Yongshi Ye, Biao Fu, Chongxuan Huang et al. · 0 citations
Open access Jul 2026

Semi-Supervised Marginal Likelihood Training with Curriculum-Guided Rewriting for Low-Resource Machine Translation

Large language models continue to face challenges in translating low-resource languages with scarce parallel data. This study investigates how to fine-tune them effectively using target-side monolingual data. Existing approaches—dominated by back-translation and recent LLM-based rewriting—remain limited by noisy synthetic sources, unguided simplification, and the absence of a principled mechanism for integrating monolingual sentences into the training objective. To address this, we developed a semi-supervised framework that integrates marginal distribution estimation and curriculum-guided rewriting to exploit monolingual data for low-resource translation. Experiments in four low-resource directions demonstrated substantial gains, averaging +8 spBLEU and +10 COMET over strong baselines, while three additional mid-resource directions showed stable improvements and consistent trends. Reference-free metrics further validated robust gains in fluency and adequacy. The findings establish a scalable paradigm for low-resource translation, revealing that the principled integration of marginal likelihood estimation and generative rewriting enables large language models to achieve superior performance under extreme data scarcity.

Wenjie Yu, Zhiqiang Yu, Zuo Jiang et al. · 0 citations
Jul 2026

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models

Heterogeneous Large Language Model (LLM) systems increasingly rely on shared contexts, retrieved evidence, and multi-agent dialogue histories, yet their internal key-value (KV) caches remain model-specific and cannot be reused across architectures. Consequently, each model must repeatedly prefill or store caches for the same context, limiting the scalability of multi-model reasoning and long-context generation. We propose Mixture-of-Translators(MoT), a cache translation framework that maps context KV caches from a source LLM into the cache space of a target LLM. Unlike prior approaches that depend on a single projection path or global shared latent space, MoT uses multiple translator modules to capture diverse source--target mappings. To further reduce residual translation error, we introduce a Context Correction Loss that aligns the replayed target trajectory with the native target trajectory. We reveal two competing failure modes in cache translation: propagated translation shift from early injection and last-state shift from late injection. MoT addresses them through translator mixtures and target-side correction. Across homogeneous and heterogeneous translations among Qwen2.5, GPT-2, and OPT models, MoT preserves downstream QA performance, including Qwen2.5-7B-scale translation with 51.0% average closed-set QA accuracy and 0.43 average extractive QA F1. In practical case studies, MoT enables quality-preserving memory reuse for multi-agent reasoning and retains 96.3% of direct-context quality in long-context cache-augmented generation, demonstrating scalable KV cache reuse across heterogeneous LLMs.

Jin-woo Lee, Minkyung Song, Junghyun Oh et al. · 3 citations
Open access Aug 2026

A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages

The effectiveness of multilingual transfer learning in low-resource settings is demonstrated by the fine-tuned Multilingual Bidirectional and Auto-Regressive Transformer-50 model, significantly outperforming the pretrained baseline.

G. Harshitha, Vasudeva, Nisha P. Poojary et al. · 0 citations
Preprint Aug 2026

Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

This paper proposes a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol for MNMT models, and reduces the vocabulary size from over 128,000 to approximately 10,000 tokens, enabling a 60% memory saving without any loss in performance.

Ahmed Amine Aliane, N. Semmar, H. Aliane · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.