Domain Adaptive Machine Translation with Synthetic Feedback for Large Language Models
Open Access
- 17 February 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (3) , 1-19
Abstract
Domain-specific machine translation (MT) significantly benefits from large language models (LLMs) due to their strong instruction-following abilities and in-context learning (ICL) capabilities. Appropriate demonstration samples and feedback are essential for helping LLMs refine their translation outputs in real-world applications. However, the scarcity of in-domain samples and professional feedback creates practical limitations. Furthermore, the current ICL paradigm does not offer the fine-grained domain features in addition to parallel translation pairs. To address these challenges, we propose a pipeline that collects in-domain translations from LLMs and generates synthetic, human-like feedback for revising these translations. The translations and their corresponding feedback are stored together to build a demonstration database, with each instance paired with the original in-domain translation and its revision. During online translation, similar in-domain translations can be retrieved as revision demonstrations. This process guides LLMs in iteratively refining their outputs by learning from demonstrations. We evaluate the proposed pipeline using open-source models like Llama3-8B-Instruct and Mistral-7B-Instruct-v0.3, on five domain-specific benchmarks for English-centric, Chinese-centric, and Portuguese-centric translation. The results demonstrate the effectiveness of the pipeline in tailoring in-domain translations and improving translation performance compared to direct translation instructions. Additionally, we discuss the experimental results from the following perspectives: (1) the effectiveness of different in-context retrieval methods; (2) the observed differences across selected domains and language; (3) the quantitative analysis of sentence-level and word-level statistics; and (4) the effect of ICL retrieval database size and decoding parameters.Keywords
Funding Information
- Science and Technology Development Fund of Macau SAR (0007/2024/AKP)
- Science and Technology Development Fund of Macau SAR (FDCT/0070/2022/AMJ)
- China Strategic Scientific and Technological Innovation Cooperation Project (2022YFE0204900)
- Science and Technology Development Fund of Macau SAR (FDCT/060/2022/AFJ)
- National Natural Science Foundation of China (62261160648)
- National Natural Science Foundation of China (62266013)
- Stanley Ho Medical Development Foundation (SHMDF-AI/2026/001)
- UM and UMDF (MYRG-GRG2024-00165-FST-UMDF, MYRG-GRG2025-00236-FST, EF2024-00185-FST, EF2023-00151-FST)
This publication has 24 references indexed in Scilit:
- Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language ModelsTransactions of the Association for Computational Linguistics, 2025
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models2023
- Towards Mitigating LLM Hallucination via Self Reflection2023
- In-context Examples Selection for Machine Translation2023
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them2023
- What Makes Good In-Context Examples for GPT-3?2022
- TICO-19: the Translation Initiative for COvid-192020
- COMET: A Neural Framework for MT Evaluation2020
- Unsupervised Domain Clusters in Pretrained Language Models2020
- News from OPUS — A collection of multilingual parallel corpora with tools and interfaces2009