{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/text-embeddings-by-weakly-supervised","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","arxiv_id":"2212.03533","date":"2022-12-07","proceeding":null,"authors":["Liang Wang","Nan Yang","Xiaolong Huang","Binxing Jiao","Linjun Yang","Daxin Jiang","Rangan Majumder","Furu Wei"],"abstract":"This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset (called CCPairs). E5 can be readily used as a general-purpose embedding model for any tasks requiring a single-vector representation of texts such as retrieval, clustering, and classification, achieving strong performance in both zero-shot and fine-tuned settings. We conduct extensive evaluations on 56 datasets from the BEIR and MTEB benchmarks. For zero-shot settings, E5 is the first model that outperforms the strong BM25 baseline on the BEIR retrieval benchmark without using any labeled data. When fine-tuned, E5 obtains the best results on the MTEB benchmark, beating existing embedding models with 40x more parameters.","url_abs":"https://arxiv.org/abs/2212.03533v2","url_pdf":"https://arxiv.org/pdf/2212.03533v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"text-embeddings-by-weakly-supervised","repo_url":"https://github.com/microsoft/unilm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mteb-benchmark","task_name":"MTEB Benchmark"},{"task_slug":"task-1-grouping","task_name":"Only Connect Walls Dataset Task 1 (Grouping)"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/task-1-grouping-on-ocw","task":"Only Connect Walls Dataset Task 1 (Grouping)","dataset":"OCW","model":"E5 (BASE)","rank_in_archive_order":11,"of":22,"metrics":{" Wasserstein Distance (WD)":"83.8 ± .6","# Correct Groups":"89 ± 6","# Solved Walls":" 1 ± 0","Adjusted Mutual Information (AMI)":"19.5 ± .4","Adjusted Rand Index (ARI)":" 16.3 ± .4","Fowlkes Mallows Score (FMS)":"33.1 ± .3"},"uses_additional_data":true},{"leaderboard":"/sota/task-1-grouping-on-ocw","task":"Only Connect Walls Dataset Task 1 (Grouping)","dataset":"OCW","model":"E5 (LARGE)","rank_in_archive_order":13,"of":22,"metrics":{" Wasserstein Distance (WD)":"84.4 ± .7","# Correct Groups":"76 ± 5","# Solved Walls":"0 ± 0","Adjusted Mutual Information (AMI)":"18.5 ± .6","Adjusted Rand Index (ARI)":"15.4 ± .5","Fowlkes Mallows Score (FMS)":"32.3 ± .4"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.03533","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}