# Retrieval-augmented generation in multilingual settings

arXiv: https://arxiv.org/abs/2407.01463 · HTML: https://mlsanity.com/paper/2407.01463/

## Key facts

- Cited by 27 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 27 of 27)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://mlsanity.com/paper/2312.15166/) (2023)
- [MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering](https://mlsanity.com/paper/2007.15207/) (2020)
- [XOR QA: Cross-lingual Open-Retrieval Question Answering](https://mlsanity.com/paper/2010.11856/) (2020)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs](https://mlsanity.com/paper/2404.13081/) (2024)
- [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://mlsanity.com/paper/2107.11976/) (2021)
- [Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability](https://mlsanity.com/paper/2306.06688/) (2023)
- ["Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2312.11361/) (2023)
- [MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages](https://mlsanity.com/paper/2207.00758/) (2022)
- [Zero-shot cross-lingual transfer in instruction tuning of large language models](https://mlsanity.com/paper/2402.14778/) (2024)
- [Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation](https://mlsanity.com/paper/2110.07150/) (2021)

## Built on by (most cited first, 27 of 27)

- [Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness](https://mlsanity.com/paper/2410.01171/) (2024)
- [Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task](https://mlsanity.com/paper/2504.03616/) (2025)
- [On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.00597/) (2025)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation](https://mlsanity.com/paper/2502.17163/) (2025)
- [Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG](https://mlsanity.com/paper/2509.13930/) (2025)
- [Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.21970/) (2024)
- [Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations](https://mlsanity.com/paper/2504.04771/) (2025)
- [LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval](https://mlsanity.com/paper/2504.16121/) (2025)
- [Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation](https://mlsanity.com/paper/2509.14477/) (2025)
- [Exploring Retrieval Augmented Generation in Arabic](https://mlsanity.com/paper/2408.07425/) (2024)
- [Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation](https://mlsanity.com/paper/2506.20869/) (2025)
- [Quality-Aware Translation Tagging in Multilingual RAG system](https://mlsanity.com/paper/2510.23070/) (2025)
- [DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering](https://mlsanity.com/paper/2603.19097/) (2026)
- [All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG](https://mlsanity.com/paper/2604.20199/) (2026)
- [XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.18886/) (2026)
- [M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG](https://mlsanity.com/paper/2512.05959/) (2025)
- [CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.25182/) (2026)
- [The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface](https://mlsanity.com/paper/2608.30052/) (2026)
- [PersianRAG: A Retrieval-Augmented Generation System for Persian Language](https://mlsanity.com/paper/2411.02832/) (2024)
- [References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation](https://mlsanity.com/paper/2505.06552/) (2025)
- [Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG](https://mlsanity.com/paper/2603.04238/) (2026)
- [Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG](https://mlsanity.com/paper/2607.02966/) (2026)
- [LAMAR: An Open Language-Aware Multilingual Alignment Reranker](https://mlsanity.com/paper/2607.22042/) (2026)
- [Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering](https://mlsanity.com/paper/2608.13160/) (2026)
- [CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering](https://mlsanity.com/paper/2609.15830/) (2026)
- [Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities](https://mlsanity.com/paper/2610.00606/) (2026)

## 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.