mlsanityData to 7 Oct 2026

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

arXiv 2409.10173 ↗First posted 16 Sep 2024cs.CL cs.AI cs.IRcited by 138

Not on the map. Why?

Cited by 24 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

32 of 47 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  9. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  10. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  11. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  12. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
20 more
  1. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
  2. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  3. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  5. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
  6. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  7. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  8. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  9. 2023Effective Long-Context Scaling of Foundation Modelscited by 301
  10. 2023Improving Text Embeddings with Large Language Modelscited by 295
  11. 2022Matryoshka Representation Learningcited by 268
  12. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 233
  13. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 180
  14. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  15. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  16. 2022RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encodercited by 118
  17. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 103
  18. 2023Scaling Sentence Embeddings with Large Language Modelscited by 83
  19. 2024Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddingscited by 20
  20. 2023Language Models are Universal Embedderscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 75; 2026: 53.

138 papers.

Sort:

By area:

  1. 2025Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergycited by 204
  2. 2025EmbeddingGemma: Powerful and Lightweight Text Representationscited by 128
  3. 2024Large Concept Models: Language Modeling in a Sentence Representation Spacecited by 86
  4. 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrievalcited by 72
  5. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 57
  6. 2025Think Then Embed: Generative Context Improves Multimodal Embeddingcited by 39
  7. 2025Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmarkcited by 37
  8. 2025KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Modelcited by 35
  9. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
  10. 2024Large Language Models Can Self-Improve in Long-context Reasoningcited by 29
  11. 2025Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representationcited by 25
  12. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generationcited by 24
38 more
  1. 2025Creative Preference Optimizationcited by 24
  2. 2025Ai2 Scholar QA: Organized Literature Synthesis with Attributioncited by 22
  3. 2025FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documentscited by 15
  4. 2025Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injectioncited by 15
  5. 2025Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systemscited by 14
  6. 2024AIR-Bench: Automated Heterogeneous Information Retrieval Benchmarkcited by 12
  7. 2025Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generationcited by 12
  8. 2025Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editingcited by 12
  9. 2025Efficient Code Embeddings from Code Generation Modelscited by 12
  10. 2024Little Giants: Synthesizing High-Quality Embedding Data at Scalecited by 11
  11. 2024Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarkscited by 10
  12. 2025FaMTEB: Massive Text Embedding Benchmark in Persian Languagecited by 10
  13. 2025SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalogcited by 10
  14. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrievalcited by 10
  15. 2025Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generationcited by 9
  16. 2025CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Modelcited by 9
  17. 2025One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Imagecited by 8
  18. 2025SEMMA: A Semantic Aware Knowledge Graph Foundation Modelcited by 7
  19. 2025RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systemscited by 7
  20. 2025LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderatorscited by 7
  21. 2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
  22. 2024TIPO: Text to Image with Text Presampling for Prompt Optimizationcited by 6
  23. 2024BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Languagecited by 6
  24. 2025LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructionscited by 6
  25. 2026ReLaGS: Relational Language Gaussian Splattingcited by 6
  26. 2024Bilingual BSARD: Extending Statutory Article Retrieval to Dutchcited by 5
  27. 2025Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generationcited by 5
  28. 2025MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutchcited by 5
  29. 2025Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecastingcited by 5
  30. 2025EntropyLong: Effective Long-Context Training via Predictive Uncertaintycited by 5
  31. 2025Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understandingcited by 5
  32. 2026CSRv2: Unlocking Ultra-Sparse Embeddingscited by 5
  33. 2025SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstractscited by 4
  34. 2025ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learningcited by 4
  35. 2025Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systemscited by 4
  36. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  37. 2025Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guaranteescited by 3
  38. 2025Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddingscited by 3

50 most cited of 138 All 138 (JSON)