paper-with-me

Papers

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task

2025-04-04 · Leonardo Ranaldi, Barry Haddow, Alexandra Birch

Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP, enhancing large language models (LLMs) by allowing them to access richer factual contexts through in-context retrieval. While effective in monolingual settings, especially in English, its use in multilingual tasks remains unexplored. This paper investigates the effectiveness of RAG across multiple languages by proposing novel approaches for multilingual open-domain question-answering. We evaluate the performance of various multilingual RAG strategies, including question-translation (tRAG), which translates questions into English before retrieval, and Multilingual RAG (MultiRAG), where retrieval occurs directly across multiple languages. Our findings reveal that tRAG, while useful, suffers from limited coverage. In contrast, MultiRAG improves efficiency by enabling multilingual retrieval but introduces inconsistencies due to cross-lingual variations in the retrieved content. To address these issues, we propose Crosslingual RAG (CrossRAG), a method that translates retrieved documents into a common language (e.g., English) before generating the response. Our experiments show that CrossRAG significantly enhances performance on knowledge-intensive tasks, benefiting both high-resource and low-resource languages.

📄 PDF Abstract BibTeX arXiv:2504.03616

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Domain Question AnsweringQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
WordPiece 설명 없음
Adam 설명 없음
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation

2025-11-13 · Bo Li, Zhenghua Xu, Rui Xie arxiv

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when t…

CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation

2026-04-28 · Rui Qi, Fengran Mo, Sijin Lu, Yufeng Chen 외 arxiv

A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Augmented Generation (RAG). However, the vanilla approach that simply c…

Reinforcement Learning

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation

2026-01-21 · Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang 외 arxiv

Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multilingual collections. However, most existing studies employ a unitive process…

Reinforcement Learning

DuetRAG: Collaborative Retrieval-Augmented Generation

2024-05-12 · Dian Jiao, Li Cai, Jingsheng Huang, Wenqiao Zhang 외

Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive tasks. However, contemporary RAG approaches …

PhilosophyRAGRetrievalRetrieval-augmented Generation

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts

2024-05-30 · Chunjing Gan, Dan Yang, Binbin Hu, Hanxiao Zhang 외

In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their a…

AllHallucinationRAGRetrieval+1