# Arctic-Embed 2.0: Multilingual Retrieval Without Compromise

arXiv: https://arxiv.org/abs/2412.04506 · HTML: https://mlsanity.com/paper/2412.04506/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [jina-embeddings-v3: Multilingual Embeddings With Task LoRA](https://mlsanity.com/paper/2409.10173/) (2024)
- [Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://mlsanity.com/paper/2310.19923/) (2023)
- [NV-Retriever: Improving text embedding models with effective hard-negative mining](https://mlsanity.com/paper/2407.15831/) (2024)
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://mlsanity.com/paper/2403.20327/) (2024)
- [Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models](https://mlsanity.com/paper/2405.05374/) (2024)
- [Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models](https://mlsanity.com/paper/2307.11224/) (2023)
- [Similarity search in the blink of an eye with compressed indices](https://mlsanity.com/paper/2304.04759/) (2023)

## Built on by (most cited first, 30 of 58)

- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Safety Pretraining: Toward the Next Generation of Safe AI](https://mlsanity.com/paper/2504.16980/) (2025)
- [Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation](https://mlsanity.com/paper/2503.01776/) (2025)
- [jina-embeddings-v5-text: Task-Targeted Embedding Distillation](https://mlsanity.com/paper/2602.15547/) (2026)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)
- [DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://mlsanity.com/paper/2502.18460/) (2025)
- [Language Models Improve When Pretraining Data Matches Target Tasks](https://mlsanity.com/paper/2507.12466/) (2025)
- [Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification](https://mlsanity.com/paper/2510.11408/) (2025)
- [EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline](https://mlsanity.com/paper/2504.03598/) (2025)
- [Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method](https://mlsanity.com/paper/2501.18539/) (2025)
- [SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog](https://mlsanity.com/paper/2504.07199/) (2025)
- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [MIRACL-VISION: A Large, multilingual, visual document retrieval benchmark](https://mlsanity.com/paper/2505.11651/) (2025)
- [Distillation versus Contrastive Learning: How to Train Your Rerankers](https://mlsanity.com/paper/2507.08336/) (2025)
- [Benchmarking Information Retrieval Models on Complex Retrieval Tasks](https://mlsanity.com/paper/2509.07253/) (2025)
- [DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search](https://mlsanity.com/paper/2607.27178/) (2026)
- [Exploiting Leaderboards for Large-Scale Distribution of Malicious Models](https://mlsanity.com/paper/2507.08983/) (2025)
- [LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum](https://mlsanity.com/paper/2601.01684/) (2026)
- [Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation](https://mlsanity.com/paper/2505.14398/) (2025)
- [Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation](https://mlsanity.com/paper/2604.03592/) (2026)
- [Larch: Learned Query Optimization for Semantic Predicates](https://mlsanity.com/paper/2606.07923/) (2026)
- [S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment](https://mlsanity.com/paper/2505.09068/) (2025)
- [Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval](https://mlsanity.com/paper/2505.19356/) (2025)
- [On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey](https://mlsanity.com/paper/2507.20783/) (2025)
- [A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems](https://mlsanity.com/paper/2512.05411/) (2025)
- [Retrieval Needs Multivectors: An Exponential Separation](https://mlsanity.com/paper/2608.21494/) (2026)
- [Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search](https://mlsanity.com/paper/2601.04646/) (2026)
- [GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification](https://mlsanity.com/paper/2503.05763/) (2025)
- [Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches](https://mlsanity.com/paper/2505.22118/) (2025)
- [DoTA-RAG: Dynamic of Thought Aggregation RAG](https://mlsanity.com/paper/2506.12571/) (2025)

## Abstract (arXiv)

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.