mlsanityData to 7 Oct 2026

Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation

arXiv 2410.21970 ↗First posted 29 Oct 2024cs.CLcited by 6

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

Abstract (arXiv)

RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has received limited research focus. In this work, we propose textitFuturepedia, a carefully crafted benchmark containing parallel texts across eight representative languages. We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. Experimental results reveal linguistic inequalities: 1) high-resource languages stand out in Monolingual Knowledge Extraction; 2) Indo-European languages lead RALMs to provide answers directly from documents, alleviating the challenge of expressing answers across languages; 3) English benefits from RALMs' selection bias and speaks louder in multilingual knowledge selection. Based on these findings, we offer advice for improving multilingual Retrieval Augmented Generation. For monolingual knowledge extraction, careful attention must be paid to cascading errors from translating low-resource languages into high-resource ones. In cross-lingual knowledge transfer, encouraging RALMs to provide answers within documents in different languages can improve transfer performance. For multilingual knowledge selection, incorporating more non-English documents and repositioning English documents can help mitigate RALMs' selection bias. Through comprehensive experiments, we underscore the complexities inherent in multilingual RALMs and offer valuable insights for future research.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 22 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

15 of 22 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models15 Nov
  2. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuning2 Oct
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 12

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  3. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  6. 2023CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languagescited by 172
  7. 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
  8. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  9. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 82
  10. 2023BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languagescited by 60
  11. 2023RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledgecited by 51
  12. 2024Retrieval-augmented generation in multilingual settingscited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generationcited by 10
  2. 2025Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGcited by 7
  3. 2025Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Componentscited by 3
  4. 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
  5. 2026When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscriptscited by 0
  6. 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. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
  3. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing
  4. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
  5. 2025XRAG: Cross-lingual Retrieval-Augmented Generation
  6. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness
  7. 2026CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation
  8. 2025The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora