Text Model¶

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@misc{xiao2024cpackpackagedresourcesadvance,
  archiveprefix = {arXiv},
  author = {Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff and Defu Lian and Jian-Yun Nie},
  eprint = {2309.07597},
  primaryclass = {cs.CL},
  title = {C-Pack: Packaged Resources To Advance General Chinese Embedding},
  url = {https://arxiv.org/abs/2309.07597},
  year = {2024},
}

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

@misc{muennighoff2024generative,
      title={Generative Representational Instruction Tuning},
      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
      year={2024},
      eprint={2402.09906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{muennighoff2024generative,
      title={Generative Representational Instruction Tuning},
      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
      year={2024},
      eprint={2402.09906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

@misc{zhao2025kalmembeddingv2,
      title={KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model},
      author={Xinping Zhao and Xinshuo Hu and Zifei Shan and Shouzheng Huang and Yao Zhou and Xin Zhang and Zetian Sun and Zhenyu Liu and Dongfang Li and Xinyuan Wei and Youcheng Pan and Yang Xiang and Meishan Zhang and Haofen Wang and Jun Yu and Baotian Hu and Min Zhang},
      year={2025},
      eprint={2506.20923},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.20923},
}

@misc{hu2025kalmembedding,
      title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
      author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
      year={2025},
      eprint={2501.01028},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.01028},
}

@misc{yu2025qzhouembeddingtechnicalreport,
      title={QZhou-Embedding Technical Report},
      author={Peng Yu and En Xu and Bin Chen and Haibiao Chen and Yinfei Xu},
      year={2025},
      eprint={2508.21632},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.21632},
}

@misc{yu2025qzhouembeddingtechnicalreport,
      title={QZhou-Embedding Technical Report},
      author={Peng Yu and En Xu and Bin Chen and Haibiao Chen and Yinfei Xu},
      year={2025},
      eprint={2508.21632},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.21632},
}

@misc{LinqAIResearch2024,
  title={Linq-Embed-Mistral:Elevating Text Retrieval with Improved GPT Data Through Task-Specific Control and Quality Refinement},
  author={Junseong Kim and Seolhwa Lee and Jihoon Kwon and Sangmo Gu and Yejin Kim and Minkyung Cho and Jy-yong Sohn and Chanyeol Choi},
  howpublished={Linq AI Research Blog},
  year={2024},
  url={https://getlinq.com/blog/linq-embed-mistral/}
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

@misc{mdbr_leaf,
  title={LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations},
  author={Robin Vujanic and Thomas Rueckstiess},
  year={2025},
  eprint={2509.12539},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2509.12539}
}

@misc{mdbr_leaf,
  title={LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations},
  author={Robin Vujanic and Thomas Rueckstiess},
  year={2025},
  eprint={2509.12539},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2509.12539}
}

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

@misc{octen2025rteb,
  title={Octen Series: Optimizing Embedding Models to #1 on RTEB Leaderboard},
  author={Octen Team},
  year={2025},
  url={https://octen-team.github.io/octen_blog/posts/octen-rteb-first-place/}
}

@misc{octen2025rteb,
  title={Octen Series: Optimizing Embedding Models to #1 on RTEB Leaderboard},
  author={Octen Team},
  year={2025},
  url={https://octen-team.github.io/octen_blog/posts/octen-rteb-first-place/}
}

@misc{octen2025rteb,
  title={Octen Series: Optimizing Embedding Models to #1 on RTEB Leaderboard},
  author={Octen Team},
  year={2025},
  url={https://octen-team.github.io/octen_blog/posts/octen-rteb-first-place/}
}

@misc{octen2025rteb,
  title={Octen Series: Optimizing Embedding Models to #1 on RTEB Leaderboard},
  author={Octen Team},
  year={2025},
  url={https://octen-team.github.io/octen_blog/posts/octen-rteb-first-place/}
}

@misc{octen2025rteb,
  title={Octen Series: Optimizing Embedding Models to #1 on RTEB Leaderboard},
  author={Octen Team},
  year={2025},
  url={https://octen-team.github.io/octen_blog/posts/octen-rteb-first-place/}
}

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

@article{shao2025reasonir,
      title={ReasonIR: Training Retrievers for Reasoning Tasks},
      author={Rulin Shao and Rui Qiao and Varsha Kishore and Niklas Muennighoff and Xi Victoria Lin and Daniela Rus and Bryan Kian Hsiang Low and Sewon Min and Wen-tau Yih and Pang Wei Koh and Luke Zettlemoyer},
      year={2025},
      journal={arXiv preprint arXiv:2504.20595},
      url={https://arxiv.org/abs/2504.20595},
}

@misc{SFR-embedding-2,
      title={SFR-Embedding-2: Advanced Text Embedding with Multi-stage Training},
      author={Rui Meng*, Ye Liu*, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, Semih Yavuz},
      year={2024},
      url={https://huggingface.co/Salesforce/SFR-Embedding-2_R}
    }

@article{liu2024codexembed,
  title={CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval},
  author={Liu, Ye and Meng, Rui and Jot, Shafiq and Savarese, Silvio and Xiong, Caiming and Zhou, Yingbo and Yavuz, Semih},
  journal={arXiv preprint arXiv:2411.12644},
  year={2024}
}

    @misc{SFRAIResearch2024,
  title={SFR-Embedding-Mistral:Enhance Text Retrieval with Transfer Learning},
  author={Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, Semih Yavuz},
  howpublished={Salesforce AI Research Blog},
  year={2024},
  url={https://www.salesforce.com/blog/sfr-embedding/}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@article{yu2024arctic,
      title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
      author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
      journal={arXiv preprint arXiv:2412.04506},
      year={2024},
      eprint={2412.04506},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2412.04506}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@article{yu2024arctic,
      title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
      author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
      journal={arXiv preprint arXiv:2412.04506},
      year={2024},
      eprint={2412.04506},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2412.04506}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

@misc{tarka_ai_research_2025,
    author       = { Tarka AI Research },
    title        = { Tarka-Embedding-150M-V1 (Revision c5f4f43) },
    year         = 2025,
    url          = { https://huggingface.co/Tarka-AIR/Tarka-Embedding-150M-V1 },
    doi          = { 10.57967/hf/6875 },
    publisher    = { Hugging Face }
}

@misc{tarka_ai_research_2025,
    author       = { Tarka AI Research },
    title        = { Tarka-Embedding-350M-V1 (Revision f4b5de8) },
    year         = 2025,
    url          = { https://huggingface.co/Tarka-AIR/Tarka-Embedding-350M-V1 },
    doi          = { 10.57967/hf/6979 },
    publisher    = { Hugging Face }
}

@misc{vectorpath2025searchmap,
  title={SearchMap: Conversational E-commerce Search Embedding Model},
  author={VectorPath Research Team},
  year={2025},
  publisher={Hugging Face},
  journal={HuggingFace Model Hub},
}

    @article{li2023angle,
      title={AnglE-optimized Text Embeddings},
      author={Li, Xianming and Li, Jing},
      journal={arXiv preprint arXiv:2309.12871},
      year={2023}
    }

@misc{snegirev2024russianfocusedembeddersexplorationrumteb,
      title={The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design},
      author={Artem Snegirev and Maria Tikhonova and Anna Maksimova and Alena Fenogenova and Alexander Abramov},
      year={2024},
      eprint={2408.12503},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2408.12503},
    }

@misc{choi2025lgaiembeddingpreviewtechnicalreport,
      title={LGAI-EMBEDDING-Preview Technical Report},
      author={Jooyoung Choi and Hyun Kim and Hansol Jang and Changwook Jun and Kyunghoon Bae and Hyewon Choi and Stanley Jungkyu Choi and Honglak Lee and Chulmin Yun},
      year={2025},
      eprint={2506.07438},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.07438},
}

@misc{mod-embedding-2025,
  title={MoD-Embedding: A Fine-tuned Multilingual Text Embedding Model},
  author={MoD Team},
  year={2025},
  url={https://huggingface.co/bflhc/MoD-Embedding}
}

@article{rankllama,
      title={Fine-Tuning LLaMA for Multi-Stage Text Retrieval},
      author={Xueguang Ma and Liang Wang and Nan Yang and Furu Wei and Jimmy Lin},
      year={2023},
      journal={arXiv:2310.08319},
}

@misc{Ruri,
  title={{Ruri: Japanese General Text Embeddings}},
  author={Hayato Tsukagoshi and Ryohei Sasano},
  year={2024},
  eprint={2409.07737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2409.07737},
}

@misc{Ruri,
  title={{Ruri: Japanese General Text Embeddings}},
  author={Hayato Tsukagoshi and Ryohei Sasano},
  year={2024},
  eprint={2409.07737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2409.07737},
}

@misc{Ruri,
  title={{Ruri: Japanese General Text Embeddings}},
  author={Hayato Tsukagoshi and Ryohei Sasano},
  year={2024},
  eprint={2409.07737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2409.07737},
}

@misc{Ruri,
  title={{Ruri: Japanese General Text Embeddings}},
  author={Hayato Tsukagoshi and Ryohei Sasano},
  year={2024},
  eprint={2409.07737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2409.07737},
}

@misc{Ruri,
  title={{Ruri: Japanese General Text Embeddings}},
  author={Hayato Tsukagoshi and Ryohei Sasano},
  year={2024},
  eprint={2409.07737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2409.07737},
}