mlsanityData to 14 Oct 2026

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

arXiv 2410.14057 ↗First posted 17 Oct 2024cs.CL cs.AIcited by 22

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In this paper, we address the problem of cross-cultural translation on two fronts: (i) we introduce XC-Translate, the first large-scale, manually-created benchmark for machine translation that focuses on text that contains potentially culturally-nuanced entity names, and (ii) we propose KG-MT, a novel end-to-end method to integrate information from a multilingual knowledge graph into a neural machine translation model by leveraging a dense retrieval mechanism. Our experiments and analyses show that current machine translation systems and large language models still struggle to translate texts containing entity names, whereas KG-MT outperforms state-of-the-art approaches by a large margin, obtaining a 129% and 62% relative improvement compared to NLLB-200 and GPT-4, respectively.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 42 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

21 of 42 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  8. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  9. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
  10. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  11. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  12. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 181
9 more
  1. 2022Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answeringcited by 72
  2. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  3. 2022Democratizing Neural Machine Translation with OPUS-MTcited by 58
  4. 2020Entity Linking in 100 Languagescited by 52
  5. 2021DEEP: DEnoising Entity Pre-training for Neural Machine Translationcited by 15
  6. 2024Beyond Correlation: Interpretable Evaluation of Machine Translation Metricscited by 10
  7. 2023Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphscited by 6
  8. 2023Code-Switching with Word Senses for Pretraining in Neural Machine Translationcited by 4
  9. 2022ParaNames: A Massively Multilingual Entity Name Corpuscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 14; 2026: 5.

22 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledgecited by 9
  2. 2025RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understandingcited by 9
  3. 2025DIWALI: Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Contextcited by 5
  4. 2025Are AI agents the new machine translation frontier? Challenges and opportunities of single- and multi-agent systems for multilingual digital communicationcited by 4
  5. 2025Towards Style Alignment in Cross-Cultural Translationcited by 4
  6. 2025Language Fusion for Parameter-Efficient Cross-lingual Transfercited by 3
  7. 2025Exploring the Translation Mechanism of Large Language Modelscited by 3
  8. 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Modelscited by 3
  9. 2024CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Modelscited by 2
  10. 2024Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)cited by 1
  11. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAGcited by 1
  12. 2026Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translationcited by 1
10 more
  1. 2025KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphscited by 0
  2. 2025HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translationcited by 0
  3. 2025Team ACK at SemEval-2025 Task 2: Beyond Word-for-Word Machine Translation for English-Korean Pairscited by 0
  4. 2025Enhancing Entity Aware Machine Translation with Multi-task Learningcited by 0
  5. 2025RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translationcited by 0
  6. 2025Toward Machine Interpreting: Lessons from Human Interpreting Studiescited by 0
  7. 2026PAUSE: Editable Strategy Artifacts for Long-Form Cultural Story Adaptationcited by 0
  8. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0
  9. 2026Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Termscited by 0
  10. 2026Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data
  2. 2025FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition
  3. 2022Adapters for Enhanced Modeling of Multilingual Knowledge and Text
  4. 2025CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
  5. 2024Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation
  6. 2025Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective
  7. 2023Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting
  8. 2024Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation