Arctic-embed 2.0: Multilingual Retrieval Without Compromise

Abstract

This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality, Arctic-Embed 2.0 delivers competitive retrieval quality on multilingual and English-only benchmarks, and supports Matryoshka Representation Learning (MRL) for efficient embedding storage with significantly lower compressed quality degradation compared to alternatives. We detail the design and implementation, presenting several important open research questions that arose during model development. We conduct experiments exploring these research questions and include extensive discussion aimed at fostering further discussion in this field.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2024arctic

Related papers

• Arctic-embed: Scalable, Efficient, And Accurate Text Embedding Models (2024)0.00
• Optimized Text Embedding Models And Benchmarks For Amharic Passage Retrieval (2025)4.94
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Freeret: Mllms As Training-free Retrievers (2025)0.00
• Tevatron 2.0: Unified Document Retrieval Toolkit Across Scale, Language, And Modality (2025)3.58
• M3-embedding: Multi-linguality, Multi-functionality, Multi-granularity Text Embeddings Through Self-knowledge Distillation (2024)19.54
• Multilingual-to-multimodal (M2M): Unlocking New Languages With Monolingual Text (2026)0.00
• Colbert-xm: A Modular Multi-vector Representation Model For Zero-shot Multilingual Information Retrieval (2024)0.00