{
 "id": "PhilipGAQ/CMedTEB",
 "owner": "PhilipGAQ",
 "name": "CMedTEB",
 "downloads": 114,
 "likes": 0,
 "last_modified": "2026-07-09T02:33:45.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval",
  "sentence-similarity"
 ],
 "citation": "@inproceedings{jiang-etal-2026-benchmarking,\n    title = \"Benchmarking and Enabling Efficient {C}hinese Medical Retrieval via Asymmetric Encoders\",\n    author = \"Jiang, Angqing  and\n      Chen, Jianlyu  and\n      Zhefang  and\n      Wang, Yongcan  and\n      Li, Xinpeng  and\n      Ding, Keyu  and\n      Lian, Defu\",\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.acl-long.916/\",\n    doi = \"10.18653/v1/2026.acl-long.916\",\n    pages = \"20000--20020\",\n    ISBN = \"979-8-89176-390-6\",\n    abstract = \"Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in real-time scenarios. Furthermore, the lack of comprehensive and high-fidelity benchmarks hinders progress in Chinese medical text retrieval. In this work, we introduce the **C**hinese **Med**ical **T**ext **E**mbedding **B**enchmark (**CMedTEB**), a benchmark spanning three kinds of practical embedding tasks: retrieval, reranking, and semantic textual similarity (STS). Dis",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "af3bf9ba582274acb0b86701e25d9a9b8be1c96e",
 "stated_evidence": "https://huggingface.co/datasets/PhilipGAQ/CMedTEB/blob/af3bf9ba582274acb0b86701e25d9a9b8be1c96e/README.md",
 "file_evidence": "https://huggingface.co/datasets/PhilipGAQ/CMedTEB/tree/af3bf9ba582274acb0b86701e25d9a9b8be1c96e",
 "card_nc": false
}