mlsanityData to 7 Oct 2026

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

arXiv 2408.16672 ↗First posted 29 Aug 2024cs.IR cs.AI cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this work we propose a number of incremental improvements to the ColBERT model architecture and training pipeline, using methods shown to work in the more mature single-vector embedding model training paradigm, particularly those that apply to heterogeneous multilingual data or boost efficiency with little tradeoff. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

27 of 34 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  9. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  10. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  11. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  12. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
15 more
  1. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  2. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  3. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  4. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  5. 2021Mr. TyDi: A Multi-lingual Benchmark for Dense Retrievalcited by 118
  6. 2021mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Datasetcited by 116
  7. 2017DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applicationscited by 110
  8. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 103
  9. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 87
  10. 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36
  11. 2022Towards Best Practices for Training Multilingual Dense Retrieval Modelscited by 26
  12. 2024Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddingscited by 20
  13. 2022Neural Approaches to Multilingual Information Retrievalcited by 18
  14. 2024JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resourcescited by 15
  15. 2024ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrievalcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 12.

25 papers.

Sort:

By area:

  1. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 70
  2. 2025jina-reranker-v3: Last but Not Late Interaction for Listwise Document Rerankingcited by 23
  3. 2025PyLate: Flexible Training and Retrieval for Late Interaction Modelscited by 17
  4. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domaincited by 16
  5. 2025Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaningcited by 10
  6. 2025MIRIAD: Augmenting LLMs with millions of medical query-response pairscited by 8
  7. 2026Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Frameworkcited by 8
  8. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  9. 2026Multi-Vector Index Compression in Any Modalitycited by 8
  10. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  11. 2026Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representationscited by 3
  12. 2026DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Searchcited by 3
13 more
  1. 2025FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generationcited by 2
  2. 2025Simple Projection Variants Improve ColBERT Performancecited by 2
  3. 2025LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026cited by 1
  4. 2025What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Modelscited by 1
  5. 2026LEMUR: Learned Multi-Vector Retrievalcited by 1
  6. 2026From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documentscited by 1
  7. 2026The Router Within: Eliciting Native Skill Routing from a Frozen LLMcited by 1
  8. 2024CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generationcited by 0
  9. 2025A model and package for German ColBERTcited by 0
  10. 2026ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annalscited by 0
  11. 2026IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressionscited by 0
  12. 2026MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkishcited by 0
  13. 2026A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generationcited by 0