홈 › Papers

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

2024-08-29 · Rohan Jha, Bo wang, Michael Günther, Georgios Mastrapas, Saba Sturua, Isabelle Mohr, Andreas Koukounas, Mohammad Kalim Akram, Nan Wang, Han Xiao

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.

📄 PDF Abstract BibTeX arXiv:2408.16672

Code (0)

등록된 구현이 없습니다.

Tasks

Information Retrieval Retrieval

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking

2025-09-29 · Feng Wang, Yuqing Li, Han Xiao arxiv

jina-reranker-v3 is a 0.6B-parameter multilingual listwise reranker that introduces a novel "last but not late" interaction. Unlike late interaction models like ColBERT that encode documents separately before multi-vecto…

jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

2024-12-11 · Andreas Koukounas, Georgios Mastrapas, Sedigheh Eslami, Bo wang 외

Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimized for crossmodal vision-language tasks a…

Contrastive Learning Cross-Modal Information Retrieval Information Retrieval Representation Learning+3

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

2024-09-16 · Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther 외

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 …

MTEB Benchmark Representation Learning Retrieval Text Matching

jina-vlm: Small Multilingual Vision Language Model

2025-12-03 · Andreas Koukounas, Georgios Mastrapas, Florian Hönicke, Sedigheh Eslami 외 arxiv

We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 la…

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

2026-02-17 · Mohammad Kalim Akram, Saba Sturua, Nastia Havriushenko, Quentin Herreros 외 arxiv

Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained with single- or multi-stage processes usi…

Information Retrieval Semantic Similarity