多语言文本嵌入模型，支持长文本且可压缩到32维仍保持高性能
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
- 采用任务专用的低秩适配器，提升不同下游任务表现
- 在MTEB上超越OpenAI、Cohere的英文性能，多语言任务优于multilingual-e5-large-instruct
- 支持1024至32维灵活压缩，基于马特约什卡表示学习
我们提出 jina-embeddings-v3，一个拥有5.7亿参数的新型文本嵌入模型，在多语言数据和长上下文检索任务中表现卓越，支持最高8192个标记的上下文长度。该模型配备一组针对特定任务的低秩适配器（LoRA），用于生成查询-文档检索、聚类、分类和文本匹配等任务的高质量嵌入。在MTEB基准测试中，jina-embeddings-v3 在英文任务上优于最新的OpenAI与Cohere专有嵌入模型，同时在所有多语言任务中均超越 multilingual-e5-large-instruct。默认输出维度为1024，用户可灵活降低至32维而性能不降，得益于马特约什卡表示学习（Matryoshka Representation Learning）。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。