mlsanityData to 7 Oct 2026

Retrieval-augmented generation in multilingual settings

arXiv 2407.01463 ↗First posted 1 Jul 2024cs.CL cs.AIcited by 27

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availability of high-quality off-the-shelf multilingual retrievers and generators, task-specific prompt engineering is needed to enable generation in user languages. Moreover, current evaluation metrics need adjustments for multilingual setting, to account for variations in spelling named entities. The main limitations to be addressed in future works include frequent code-switching in non-Latin alphabet languages, occasional fluency errors, wrong reading of the provided documents, or irrelevant retrieval. We release the code for the resulting mRAG baseline pipeline at https://github.com/naver/bergen.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 32 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

27 of 32 references.

References · 27

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  7. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  8. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  9. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  10. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  11. 2023Active Retrieval Augmented Generationcited by 506
  12. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
15 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  2. 2016FastText.zip: Compressing text classification modelscited by 331
  3. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  4. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  5. 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
  6. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 151
  7. 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
  8. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 82
  9. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  10. 2021One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrievalcited by 46
  11. 2023Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Abilitycited by 27
  12. 2023"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generationcited by 12
  13. 2022MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languagescited by 11
  14. 2024Zero-shot cross-lingual transfer in instruction tuning of large language modelscited by 10
  15. 2021Cross-Lingual Open-Domain Question Answering with Answer Sentence Generationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 12; 2026: 11.

27 papers.

Sort:

By area:

  1. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustnesscited by 13
  2. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Taskcited by 12
  3. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generationcited by 10
  4. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  5. 2025MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generationcited by 7
  6. 2025Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGcited by 7
  7. 2024Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generationcited by 6
  8. 2025LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrievalcited by 5
  9. 2024Exploring Retrieval Augmented Generation in Arabiccited by 4
  10. 2025Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentationscited by 4
  11. 2025Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluationcited by 4
  12. 2025Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluationcited by 3
15 more
  1. 2025Quality-Aware Translation Tagging in Multilingual RAG systemcited by 3
  2. 2026DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answeringcited by 3
  3. 2026XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generationcited by 2
  4. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGcited by 2
  5. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAGcited by 1
  6. 2026CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generationcited by 1
  7. 2026The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interfacecited by 1
  8. 2024PersianRAG: A Retrieval-Augmented Generation System for Persian Languagecited by 0
  9. 2025References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulationcited by 0
  10. 2026Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAGcited by 0
  11. 2026Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAGcited by 0
  12. 2026LAMAR: An Open Language-Aware Multilingual Alignment Rerankercited by 0
  13. 2026Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answeringcited by 0
  14. 2026CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answeringcited by 0
  15. 2026Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Investigating Language Preference of Multilingual RAG Systems
  2. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research
  3. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  4. 2024Multi-Head RAG: Solving Multi-Aspect Problems with LLMs
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  6. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  7. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  8. 2024RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation