KURE-v2-unsupervised

KURE-v2-unsupervised is the stage-1 checkpoint for KURE-v2: a Korean-English late-interaction (ColBERT) encoder trained with unsupervised contrastive learning only, on 20.7M query–document pairs.

What this is for

If you would like to train your own late-interaction retriever for Korean-English and would rather not start from a masked-LM backbone, feel free to use this model. We highly recommend not deploying it as-is.

Evaluation

nDCG@10 on the nine MTEB(kor, v2) retrieval tasks. We report average nDCG@10.

Model	Params	Avg	AutoRAG	PubHealthQA	Ko-StrategyQA	LawIRKo	SQuADKorV1	Belebele (ko-ko)	MrTidy	MLDR	MIRACL
Our Models
nlpai-lab/KURE-v2	154M	0.8160	0.9718	0.8229	0.8070	0.7550	0.9846	0.9660	0.5974	0.7159	0.7237
nlpai-lab/KURE-v2-unsupervised	154M	0.7283	0.8822	0.8240	0.7818	0.7680	0.9427	0.9525	0.3496	0.6130	0.4411
Late-Interaction (Multi-Vector) Models
yjoonjang/colbert-ko-en-v2	149M	0.8063	0.9686	0.8222	0.7940	0.7181	0.9846	0.9687	0.5783	0.6992	0.7230
lightonai/mLateOn	307M	0.7906	0.9392	0.8061	0.7905	0.6431	0.9803	0.9608	0.5817	0.7005	0.7135
perplexity-ai/pplx-embed-v1-late-0.6b	596M	0.7381	0.8557	0.8089	0.7973	0.7285	0.9696	0.9548	0.5400	0.2816	0.7064
dragonkue/colbert-ko-0.1b	149M	0.6776	0.9700	0.7482	0.7364	0.4475	0.9794	0.9644	0.3966	0.2872	0.5685
yjoonjang/colbert-ko-v1	149M	0.6282	0.9557	0.6783	0.6560	0.4823	0.9594	0.9154	0.3279	0.2214	0.4575
Dense (Single-Vector) Models
sionic-ai/comsat-embed-ko-8b-preview	7.6B	0.7927	0.8518	0.8871	0.8394	0.8164	0.9168	0.9853	0.6253	0.5157	0.6964
Qwen/Qwen3-Embedding-8B	7.6B	0.7826	0.8276	0.8721	0.8363	0.8171	0.9063	0.9824	0.6187	0.5046	0.6783
Qwen/Qwen3-Embedding-4B	4.0B	0.7737	0.8431	0.8693	0.8270	0.7769	0.9044	0.9522	0.6076	0.5022	0.6803
microsoft/harrier-oss-v1-27b	27.0B	0.7667	0.8176	0.8971	0.8361	0.8737	0.9204	0.9546	0.5306	0.4046	0.6653
dragonkue/snowflake-arctic-embed-l-v2.0-ko	568M	0.7653	0.9093	0.8337	0.8050	0.7735	0.9447	0.9518	0.5712	0.4304	0.6685
codefuse-ai/F2LLM-v2-8B	7.6B	0.7638	0.7678	0.9380	0.8371	0.8405	0.8874	0.9513	0.6162	0.4047	0.6313
telepix/PIXIE-Rune-v1.5	568M	0.7618	0.8927	0.8426	0.8064	0.7705	0.9457	0.9617	0.5492	0.4482	0.6393
nlpai-lab/KURE-v1	568M	0.7616	0.8708	0.8193	0.7999	0.7426	0.9357	0.9502	0.5909	0.4637	0.6816
dragonkue/BGE-m3-ko	568M	0.7547	0.8738	0.8155	0.7959	0.7322	0.9414	0.9503	0.6099	0.3899	0.6833
BAAI/bge-m3	568M	0.7509	0.8301	0.8041	0.7941	0.7174	0.9038	0.9316	0.6471	0.4287	0.7015
nlpai-lab/KoE5	560M	0.7337	0.8434	0.8351	0.8001	0.7756	0.8980	0.9425	0.5841	0.3015	0.6235

Late-interaction rows were measured with mteb 2.18.16 and PLAID retrieval, and single-vector rows are taken from the official MTEB results repository, except for Belebele, where only the Korean-query / Korean-corpus subset is used. The original version also includes cross-lingual subsets (Korean query – English corpus, English query – Korean corpus).

Citation

@misc{kure-v2,
  title  = {KURE-v2: a Korean-English bilingual late-interaction retriever},
  author = {Jang, Youngjoon and Son, Junyoung and Lee, Taemin and Hong, Seongtae and Lim, Heuiseok},
  year   = {2026},
  url    = {https://huggingface.co/nlpai-lab/KURE-v2},
}

@inproceedings{jang2025kure,
  title={KURE: Embedding Model for Korean-Specific Retrieval},
  author={Jang, Youngjoon and Son, Junyoung and Lee, Taemin and Hong, Seongtae and Park, JeongBae and Lim, Heuiseok},
  booktitle={Annual Conference on Human and Language Technology},
  pages={129--134},
  year={2025},
  organization={Human and Language Technology}
}

@inproceedings{santhanam-etal-2022-colbertv2,
  title     = {ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction},
  author    = {Santhanam, Keshav and Khattab, Omar and Saad-Falcon, Jon and Potts, Christopher and Zaharia, Matei},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year      = {2022},
  pages     = {3715--3734},
}

@misc{PyLate,
  title  = {PyLate: Flexible Training and Retrieval for Late Interaction Models},
  author = {Chaffin, Antoine and Sourty, Raphaël},
  year   = {2024},
  url    = {https://github.com/lightonai/pylate},
}