mlsanityData to 7 Oct 2026

Arctic-Embed 2.0: Multilingual Retrieval Without Compromise

arXiv 2412.04506 ↗First posted 3 Dec 2024cs.CL cs.IR cs.LGcited by 57

Not on the map. Why?

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.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

18 of 35 references.

References · 18

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  5. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  6. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
  7. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  8. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  9. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 255
  10. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  11. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 233
  12. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 138
6 more
  1. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 103
  2. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 83
  3. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
  4. 2024Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Modelscited by 60
  5. 2023Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Modelscited by 35
  6. 2023Similarity search in the blink of an eye with compressed indicescited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 27; 2026: 30.

57 papers.

Sort:

By area:

  1. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 98
  2. 2025Safety Pretraining: Toward the Next Generation of Safe AIcited by 35
  3. 2025Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representationcited by 25
  4. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  5. 2025DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrieverscited by 19
  6. 2026jina-embeddings-v5-text: Task-Targeted Embedding Distillationcited by 19
  7. 2025Language Models Improve When Pretraining Data Matches Target Taskscited by 18
  8. 2025Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectificationcited by 17
  9. 2025EnrichIndex: Using LLMs to Enrich Retrieval Indices Offlinecited by 15
  10. 2025Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Methodcited by 10
  11. 2025SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalogcited by 10
  12. 2025Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaningcited by 10
38 more
  1. 2025MIRACL-VISION: A Large, multilingual, visual document retrieval benchmarkcited by 9
  2. 2025Distillation versus Contrastive Learning: How to Train Your Rerankerscited by 6
  3. 2025Benchmarking Information Retrieval Models on Complex Retrieval Taskscited by 6
  4. 2025Exploiting Leaderboards for Large-Scale Distribution of Malicious Modelscited by 5
  5. 2026LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculumcited by 5
  6. 2025Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computationcited by 4
  7. 2026Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptationcited by 4
  8. 2025S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessmentcited by 3
  9. 2025Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrievalcited by 3
  10. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  11. 2025A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systemscited by 3
  12. 2026DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Searchcited by 3
  13. 2025GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classificationcited by 1
  14. 2025Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approachescited by 1
  15. 2025DoTA-RAG: Dynamic of Thought Aggregation RAGcited by 1
  16. 2025Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discoverycited by 1
  17. 2026An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fitcited by 1
  18. 2026CORE-T: COherent REtrieval of Tables for Text-to-SQLcited by 1
  19. 2026Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarkscited by 1
  20. 2026Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadithcited by 1
  21. 2026Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMscited by 1
  22. 2026Xetrieval: Mechanistically Explaining Dense Retrievalcited by 1
  23. 2026Larch: Learned Query Optimization for Semantic Predicatescited by 1
  24. 2026Closing the Operational Gap in Semantic Cachingcited by 1
  25. 2026Retrieval Needs Multivectors: An Exponential Separationcited by 1
  26. 2025Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddingscited by 0
  27. 2025WeatherArchive-Bench: Benchmarking Retrieval-Augmented Reasoning for Historical Weather Archivescited by 0
  28. 2025Eigenfunction Extraction for Ordered Representation Learningcited by 0
  29. 2026STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmarkcited by 0
  30. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMscited by 0
  31. 2026Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Searchcited by 0
  32. 2026Generating consensus and dissent on massive discussion platforms with a semantic-vector modelcited by 0
  33. 2026Quantifying Retriever-Generator Alignment in RAG with Local Explanationscited by 0
  34. 2026Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Taskcited by 0
  35. 2026QOuLiPo: What a quantum computer sees when it reads a bookcited by 0
  36. 2026The Multilingual Curse at the Retrieval Layer: Evidence from Amhariccited by 0
  37. 2026MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integrationcited by 0
  38. 2026SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptationcited by 0

50 most cited of 57 All 57 (JSON)