mlsanityData to 7 Oct 2026

Investigating Language Preference of Multilingual RAG Systems

arXiv 2502.11175 ↗First posted 16 Feb 2025cs.CLcited by 22

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

Abstract (arXiv)

Multilingual Retrieval-Augmented Generation (mRAG) systems enhance language models by integrating external multilingual information to produce context-aware responses. However, mRAG systems struggle with retrieving relevant information due to linguistic variations between queries and documents, generating inconsistent responses when multilingual sources conflict. In this work, we systematically investigate language preferences in both retrieval and generation of mRAG through a series of experiments. Our analysis indicates that retrievers tend to prefer high-resource and query languages, yet this preference does not consistently improve generation performance. Moreover, we observe that generators prefer the query language or Latin scripts, leading to inconsistent outputs. To overcome these issues, we propose Dual Knowledge Multilingual RAG (DKM-RAG), a simple yet effective framework that fuses translated multilingual passages with complementary model knowledge. Empirical results demonstrate that DKM-RAG mitigates language preference in generation and enhances performance across diverse linguistic settings. Code is available at https://github.com/jeonghyunpark2002/LanguagePreference.git

Key facts. Cited by 22 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 11 of its 28 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

11 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  5. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 151
  6. 2024Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontiercited by 121
  7. 2023Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Modelscited by 117
  8. 2024Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languagescited by 36
  9. 2022Are Pretrained Multilingual Models Equally Fair Across Languages?cited by 8
  10. 2024Language Fairness in Multilingual Information Retrievalcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 15.

22 papers.

Sort:

By area:

  1. 2025CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Modelscited by 17
  2. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generationcited by 10
  3. 2025Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGcited by 7
  4. 2025The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corporacited by 4
  5. 2025Quality-Aware Translation Tagging in Multilingual RAG systemcited by 3
  6. 2026DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answeringcited by 3
  7. 2025Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Modelscited by 2
  8. 2026Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusioncited by 2
  9. 2026Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generationcited by 2
  10. 2026CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-trainingcited by 2
  11. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGcited by 2
  12. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAGcited by 1
10 more
  1. 2026When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Modelscited by 1
  2. 2026CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generationcited by 1
  3. 2026Code-Switching Reveals Language Anchoring in Multilingual LLMscited by 1
  4. 2026CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAGcited by 0
  5. 2026MIMO: Multilingual Information Retrieval via Monolingual Objectivescited by 0
  6. 2026SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrievalcited by 0
  7. 2026Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAGcited by 0
  8. 2026LAMAR: An Open Language-Aware Multilingual Alignment Rerankercited by 0
  9. 2026Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answeringcited by 0
  10. 2026Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval-augmented generation in multilingual settings
  2. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
  3. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  4. 2024Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprise
  5. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  6. 2025Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  8. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness