Boosting Data Utilization For Multilingual Dense Retrieval

Abstract

Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtaining high-quality hard negative samples and effective mini-batch data. The extensive experimental results on a multilingual retrieval benchmark, MIRACL, with 16 languages demonstrate the effectiveness of our method by outperforming several existing strong baselines.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2025boosting

Related papers

• What Drives Cross-lingual Ranking? Retrieval Approaches With Multilingual Language Models (2025)0.00
• Unsupervised Dense Information Retrieval With Contrastive Learning (2021)0.00
• Soft Prompt Decoding For Multilingual Dense Retrieval (2023)7.50
• Boosting Zero-shot Cross-lingual Retrieval By Training On Artificially Code-switched Data (2023)4.52
• Colbert-xm: A Modular Multi-vector Representation Model For Zero-shot Multilingual Information Retrieval (2024)0.00
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Empowering Dual-encoder With Query Generator For Cross-lingual Dense Retrieval (2023)6.34
• Freeret: Mllms As Training-free Retrievers (2025)0.00