{"work":{"id":"b2004e20-1b24-4c37-9fad-dfdd9a7a8fee","openalex_id":"https://openalex.org/W4391709827","doi":"10.48550/arxiv.2402.05672","arxiv_id":"2402.05672","raw_key":null,"title":"Multilingual E5 Text Embeddings: A Technical Report","authors":null,"authors_text":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei","year":2024,"venue":"cs.CL","abstract":"This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023. Three embedding models of different sizes (small / base / large) are provided, offering a balance between the inference efficiency and embedding quality. The training procedure adheres to the English E5 model recipe, involving contrastive pre-training on 1 billion multilingual text pairs, followed by fine-tuning on a combination of labeled datasets. Additionally, we introduce a new instruction-tuned embedding model, whose performance is on par with state-of-the-art, English-only models of similar sizes. Information regarding the model release can be found at https://github.com/microsoft/unilm/tree/master/e5 .","external_url":"https://arxiv.org/abs/2402.05672","cited_by_count":35,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2402.05672","created_at":"2026-05-09T19:45:54.246650+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Multilingual E5 Text Embeddings: A Technical Report","render_title":"Multilingual E5 Text Embeddings: A Technical Report"},"hub":{"state":{"work_id":"b2004e20-1b24-4c37-9fad-dfdd9a7a8fee","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":82,"external_cited_by_count":35,"distinct_field_count":12,"first_pith_cited_at":"2025-02-04T21:43:16+00:00","last_pith_cited_at":"2026-07-07T14:47:42+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T09:29:24.789992+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"method","n":6},{"context_role":"baseline","n":4},{"context_role":"background","n":2},{"context_role":"dataset","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"use_method","n":6},{"context_polarity":"baseline","n":4},{"context_polarity":"background","n":2},{"context_polarity":"unclear","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}