{
 "id": "QuangDuy/supervised_data-hn-rerank-denoise",
 "owner": "QuangDuy",
 "name": "supervised_data-hn-rerank-denoise",
 "downloads": 99,
 "likes": 0,
 "last_modified": "2026-10-25T15:38:24.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "sentence-similarity",
  "feature-extraction"
 ],
 "citation": "@misc{qu2021rocketqaoptimizedtrainingapproach,\r\n      title={RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering},\r\n      author={Yingqi Qu and Yuchen Ding and Jing Liu and Kai Liu and Ruiyang Ren and Wayne Xin Zhao and Daxiang Dong and Hua Wu and Haifeng Wang},\r\n      year={2021},\r\n      eprint={2010.08191},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CL},\r\n      url={https://arxiv.org/abs/2010.08191},\r\n}\r\n\r\n@misc{thakur2025hardnegativeshardlessons,\r\n      title={Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs},\r\n      author={Nandan Thakur and Crystina Zhang and Xueguang Ma and Jimmy Lin},\r\n      year={2025},\r\n      eprint={2505.16967},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.IR},\r\n      url={https://arxiv.org/abs/2505.16967},\r\n}\r\n\r\n@misc{wang2024multilinguale5textembeddings,\r\n      title={Multilingual E5 Text Embeddings: A Technical Report},\r\n      author={Liang Wang and Nan Yang and Xiaolong Huang and Linjun Yang and Rangan Majumder and Furu Wei},\r\n      year={2024},\r\n      eprint={2402.05672},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CL},\r\n      url={https://arxiv.org/abs/2402.05672},\r\n}\r\n\r\n@misc{chen2025m3embeddingmultilingualitymultifunctionalitymultigranularity,\r\n      title={M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},\r\n      author={Jianlv Chen",
 "signal": "restrictive",
 "reason": "The dataset card's licence name or licence section contains wording that suggests non-commercial, research-only or academic-only use restrictions.",
 "revision": "3877a487c1eb2a02052c7005e40286df4a53fe1c",
 "stated_evidence": "https://huggingface.co/datasets/QuangDuy/supervised_data-hn-rerank-denoise/blob/3877a487c1eb2a02052c7005e40286df4a53fe1c/README.md",
 "file_evidence": "https://huggingface.co/datasets/QuangDuy/supervised_data-hn-rerank-denoise/tree/3877a487c1eb2a02052c7005e40286df4a53fe1c",
 "card_nc": true
}