Lune

EMNLP Findings2025

Retrieval-Augmented Machine Translation with Unstructured Knowledge

Jiaan Wang, Fandong Meng, Yingxue Zhang, Jie Zhou

Abstract

Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs). In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific knowledge from knowledge graphs, to enhance MT models. However, a large amount of world knowledge is organized in unstructured documents, and might not be fully paired across different languages. In this paper, we study retrieval-augmented MT using unstructured documents. Specifically, we build RAGtrans, the first benchmark to train and evaluate LLMs' retrieval-augmented MT ability. RAGtrans contains 169K MT samples collected via GPT-4o and human translators. Besides, documents from various languages are also provided to supply the knowledge to these samples. Based on RAGtrans, we further propose a multi-task training method to teach LLMs how to use information from multilingual documents during their translation. The method uses existing multilingual corpora to create auxiliary training objectives without additional labeling requirements. Extensive experiments show that the method improves LLMs by 1.6∼3.1 BLEU and 1.0∼2.0 COMET scores in En⇒Zh, and 1.7∼2.9 BLEU and 2.1∼2.7 COMET scores in En⇒De. We also conclude the critical difficulties that current LLMs face with this task. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation cites Nearest Neighbor Machine Translation
  • Self-Knowledge Guided Retrieval Augmentation for Large Language Models cites Dense Passage Retrieval for Open-Domain Question Answering
  • Self-Knowledge Guided Retrieval Augmentation for Large Language Models cites Nearest Neighbor Machine Translation
  • M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation cites Dense Passage Retrieval for Open-Domain Question Answering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity TranslationJiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong et al.ACL 2026 · 2 citations
  2. Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine TranslationSherrie Shen, Weixuan Wang, Alexandra BirchEMNLP 2025
  3. Towards Style Alignment in Cross-Cultural TranslationShreya Havaldar, Adam Stein, Eric Wong, Lyle H. UngarACL 2025

Builds on10

  1. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  2. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationJianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo et al.ACL Findings 2024 · 762 citations
  3. Nearest Neighbor Machine TranslationUrvashi Khandelwal, Angela Fan, Dan Jurafsky, Luke Zettlemoyer et al.ICLR 2021 · 323 citations
  4. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
  5. Self-Knowledge Guided Retrieval Augmentation for Large Language ModelsYile Wang, Peng Li, Maosong Sun, Yang LiuEMNLP Findings 2023 · 62 citations

Related papers

  1. MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG ConversationsSara Rosenthal, Yannis Katsis, Vraj Shah, Lihong He et al.ACL Findings 2026
  2. Benchmarking Retrieval-Augmented Generation in Multi-Modal ContextsZhenghao Liu, Xingsheng Zhu, Tianshuo Zhou, Xinyi Zhang et al.ACM MM 2025 · 4 citations
  3. RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and BenchmarkingJiaru Zou, Dongqi Fu, Sirui Chen, Xinrui He et al.ACL Findings 2026
  4. Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented GenerationShicheng Xu, Liang Pang, Mo Yu, Fandong Meng et al.ACL 2024
  5. M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAGDavid Anugraha, Patrick Amadeus Irawan, Anshul Singh, En-Shiun Annie Lee et al.CVPR 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines