mteb 2.4.1__py3-none-any.whl → 2.4.2__py3-none-any.whl

mteb/models/model_implementations/gte_models.py

@@ -89,6 +89,12 @@ gte_qwen1_5_7b_instruct = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    citation="""@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}
+}""",
 )
 
 gte_qwen2_1_5b_instruct = ModelMeta(
@@ -119,6 +125,12 @@ gte_qwen2_1_5b_instruct = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    citation="""@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}
+}""",
 )
 
 gte_small_zh = ModelMeta(
@@ -140,6 +152,12 @@ gte_small_zh = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,  # Not disclosed
+    citation="""@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}
+}""",
 )
 
 gte_base_zh = ModelMeta(
@@ -161,6 +179,12 @@ gte_base_zh = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,  # Not disclosed
+    citation="""@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}
+}""",
 )
 
 gte_large_zh = ModelMeta(
@@ -182,6 +206,12 @@ gte_large_zh = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,  # Not disclosed
+    citation="""@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}
+}""",
 )
 
 gte_multilingual_langs = [
@@ -304,6 +334,13 @@ gte_multilingual_base = ModelMeta(
     public_training_code=None,
     public_training_data=None,  # couldn't find
     training_datasets=gte_multi_training_data,
+    citation="""@inproceedings{zhang2024mgte,
+  title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
+  author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
+  booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
+  pages={1393--1412},
+  year={2024}
+}""",
 )
 
 gte_modernbert_base = ModelMeta(
@@ -325,6 +362,20 @@ gte_modernbert_base = ModelMeta(
     public_training_code=None,  # couldn't find
     public_training_data=None,
     training_datasets=gte_multi_training_data,  # English part of gte_multi_training_data,
+    citation="""@inproceedings{zhang2024mgte,
+  title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
+  author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
+  booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
+  pages={1393--1412},
+  year={2024}
+}
+
+@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}
+}""",
 )
 
 
@@ -349,4 +400,22 @@ gte_base_en_v15 = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    citation="""@misc{zhang2024mgte,
+  title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval}, 
+  author={Xin Zhang and Yanzhao Zhang and Dingkun Long and Wen Xie and Ziqi Dai and Jialong Tang and Huan Lin and Baosong Yang and Pengjun Xie and Fei Huang and Meishan Zhang and Wenjie Li and Min Zhang},
+  year={2024},
+  eprint={2407.19669},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2407.19669}, 
+}
+@misc{li2023gte,
+  title={Towards General Text Embeddings with Multi-stage Contrastive Learning}, 
+  author={Zehan Li and Xin Zhang and Yanzhao Zhang and Dingkun Long and Pengjun Xie and Meishan Zhang},
+  year={2023},
+  eprint={2308.03281},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2308.03281}, 
+}""",
 )

mteb/models/model_implementations/kalm_models.py

@@ -901,6 +901,25 @@ KaLM_Embedding_KaLM_embedding_multilingual_mini_instruct_v2_5 = ModelMeta(
     training_datasets=kalm_v2_training_data,
     adapted_from="HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2",
     superseded_by=None,
+    citation="""@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}, 
+}""",
 )
 
 KaLM_Embedding_gemma_3_12b_2511 = ModelMeta(
@@ -928,4 +947,23 @@ KaLM_Embedding_gemma_3_12b_2511 = ModelMeta(
     public_training_code="https://github.com/HITsz-TMG/KaLM-Embedding",
     public_training_data=None,
     training_datasets=KaLM_Embedding_gemma_3_12b_training_data,
+    citation="""@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}, 
+}""",
 )

mteb/models/model_implementations/kblab.py

@@ -21,4 +21,10 @@ sbert_swedish = ModelMeta(
     public_training_data=None,
     training_datasets=None,
     adapted_from="sentence-transformers/all-mpnet-base-v2",
+    citation="""@misc{rekathati2021introducing,  
+  author = {Rekathati, Faton},  
+  title = {The KBLab Blog: Introducing a Swedish Sentence Transformer},  
+  url = {https://kb-labb.github.io/posts/2021-08-23-a-swedish-sentence-transformer/},  
+  year = {2021}  
+}""",
 )

mteb/models/model_implementations/kowshik24_models.py

@@ -19,4 +19,13 @@ kowshik24_bangla_embedding_model = ModelMeta(
     public_training_code="https://github.com/kowshik24/Bangla-Embedding",
     public_training_data="https://huggingface.co/datasets/sartajekram/BanglaRQA",
     training_datasets=set(),
+    citation="""@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}""",
 )