mteb 2.4.1__py3-none-any.whl → 2.5.0__py3-none-any.whl

mteb/models/model_implementations/dino_models.py

@@ -123,6 +123,14 @@ dinov2_small = ModelMeta(
     similarity_fn_name=ScoringFunction.COSINE,
     use_instructions=False,
     training_datasets=dinov2_training_datasets,
+    citation="""@misc{oquab2023dinov2,
+      title={DINOv2: Learning Robust Visual Features without Supervision}, 
+      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
+      year={2023},
+      eprint={2304.07193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}""",
 )
 
 dinov2_base = ModelMeta(
@@ -145,6 +153,14 @@ dinov2_base = ModelMeta(
     similarity_fn_name=ScoringFunction.COSINE,
     use_instructions=False,
     training_datasets=dinov2_training_datasets,
+    citation="""@misc{oquab2023dinov2,
+      title={DINOv2: Learning Robust Visual Features without Supervision}, 
+      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
+      year={2023},
+      eprint={2304.07193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}""",
 )
 
 dinov2_large = ModelMeta(
@@ -167,6 +183,14 @@ dinov2_large = ModelMeta(
     similarity_fn_name=ScoringFunction.COSINE,
     use_instructions=False,
     training_datasets=dinov2_training_datasets,
+    citation="""@misc{oquab2023dinov2,
+      title={DINOv2: Learning Robust Visual Features without Supervision}, 
+      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
+      year={2023},
+      eprint={2304.07193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}""",
 )
 
 dinov2_giant = ModelMeta(
@@ -189,6 +213,14 @@ dinov2_giant = ModelMeta(
     similarity_fn_name=ScoringFunction.COSINE,
     use_instructions=False,
     training_datasets=dinov2_training_datasets,
+    citation="""@misc{oquab2023dinov2,
+      title={DINOv2: Learning Robust Visual Features without Supervision}, 
+      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
+      year={2023},
+      eprint={2304.07193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino_training_datasets = set(
@@ -215,6 +247,14 @@ webssl_dino300m_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino1b_full2b = ModelMeta(
@@ -237,6 +277,14 @@ webssl_dino1b_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino2b_full2b = ModelMeta(
@@ -259,6 +307,14 @@ webssl_dino2b_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino3b_full2b = ModelMeta(
@@ -281,6 +337,14 @@ webssl_dino3b_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino5b_full2b = ModelMeta(
@@ -303,6 +367,14 @@ webssl_dino5b_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino7b_full8b_224 = ModelMeta(
@@ -325,6 +397,14 @@ webssl_dino7b_full8b_224 = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino7b_full8b_378 = ModelMeta(
@@ -347,6 +427,14 @@ webssl_dino7b_full8b_378 = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino7b_full8b_518 = ModelMeta(
@@ -369,6 +457,14 @@ webssl_dino7b_full8b_518 = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 
@@ -392,6 +488,14 @@ webssl_dino2b_light2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino2b_heavy2b = ModelMeta(
@@ -414,6 +518,14 @@ webssl_dino2b_heavy2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino3b_light2b = ModelMeta(
@@ -436,6 +548,14 @@ webssl_dino3b_light2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_dino3b_heavy2b = ModelMeta(
@@ -458,6 +578,14 @@ webssl_dino3b_heavy2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_mae300m_full2b = ModelMeta(
@@ -480,6 +608,14 @@ webssl_mae300m_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_mae700m_full2b = ModelMeta(
@@ -502,6 +638,14 @@ webssl_mae700m_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )
 
 webssl_mae1b_full2b = ModelMeta(
@@ -524,4 +668,12 @@ webssl_mae1b_full2b = ModelMeta(
     similarity_fn_name=None,
     use_instructions=False,
     training_datasets=webssl_dino_training_datasets,
+    citation="""@article{fan2025scaling,
+  title={Scaling Language-Free Visual Representation Learning}, 
+  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
+  year={2025},
+  eprint={2504.01017},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}""",
 )

mteb/models/model_implementations/emillykkejensen_models.py

@@ -21,6 +21,15 @@ embedding_gemma_300m_scandi = ModelMeta(
     similarity_fn_name="cosine",  # type: ignore[arg-type]
     adapted_from="google/embeddinggemma-300m",
     memory_usage_mb=578,
+    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",
+}""",
 )
 
 
@@ -67,4 +76,13 @@ mmbert_scandi = ModelMeta(
     training_datasets=set(),
     similarity_fn_name="cosine",  # type: ignore[arg-type]
     adapted_from="jonasaise/scandmmBERT-base-scandinavian",
+    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",
+}""",
 )

mteb/models/model_implementations/euler_models.py

@@ -22,4 +22,10 @@ Euler_Legal_Embedding_V1 = ModelMeta(
     training_datasets=set(),  # final-data-new-anonymized-grok4-filtered
     adapted_from="Qwen/Qwen3-Embedding-8B",
     superseded_by=None,
+    citation="""@misc{euler2025legal,
+      title={Euler-Legal-Embedding: Advanced Legal Representation Learning}, 
+      author={LawRank Team},
+      year={2025},
+      publisher={Hugging Face}
+}""",
 )

mteb/models/model_implementations/fa_models.py

@@ -156,6 +156,15 @@ tooka_sbert = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    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",
+}""",
 )
 
 fa_bert = ModelMeta(
@@ -180,6 +189,29 @@ fa_bert = ModelMeta(
         # It's just a base model
         # https://huggingface.co/datasets/sbunlp/hmblogs-v3
     ),
+    citation="""@inproceedings{masumi-etal-2025-fabert,
+    title = "{F}a{BERT}: Pre-training {BERT} on {P}ersian Blogs",
+    author = "Masumi, Mostafa  and
+      Majd, Seyed Soroush  and
+      Shamsfard, Mehrnoush  and
+      Beigy, Hamid",
+    editor = "Bak, JinYeong  and
+      Goot, Rob van der  and
+      Jang, Hyeju  and
+      Buaphet, Weerayut  and
+      Ramponi, Alan  and
+      Xu, Wei  and
+      Ritter, Alan",
+    booktitle = "Proceedings of the Tenth Workshop on Noisy and User-generated Text",
+    month = may,
+    year = "2025",
+    address = "Albuquerque, New Mexico, USA",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.wnut-1.10/",
+    doi = "10.18653/v1/2025.wnut-1.10",
+    pages = "85--96",
+    ISBN = "979-8-89176-232-9",
+}""",
 )
 
 tooka_sbert_v2_small = ModelMeta(
@@ -201,6 +233,15 @@ tooka_sbert_v2_small = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    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",
+}""",
 )
 
 tooka_sbert_v2_large = ModelMeta(
@@ -222,4 +263,13 @@ tooka_sbert_v2_large = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,
+    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",
+}""",
 )

mteb/models/model_implementations/facebookai.py

@@ -123,6 +123,28 @@ xlmr_base = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=set(),
+    citation="""@article{DBLP:journals/corr/abs-1911-02116,
+  author    = {Alexis Conneau and
+               Kartikay Khandelwal and
+               Naman Goyal and
+               Vishrav Chaudhary and
+               Guillaume Wenzek and
+               Francisco Guzm{\'{a}}n and
+               Edouard Grave and
+               Myle Ott and
+               Luke Zettlemoyer and
+               Veselin Stoyanov},
+  title     = {Unsupervised Cross-lingual Representation Learning at Scale},
+  journal   = {CoRR},
+  volume    = {abs/1911.02116},
+  year      = {2019},
+  url       = {http://arxiv.org/abs/1911.02116},
+  eprinttype = {arXiv},
+  eprint    = {1911.02116},
+  timestamp = {Mon, 11 Nov 2019 18:38:09 +0100},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-1911-02116.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}""",
 )
 
 xlmr_large = ModelMeta(
@@ -144,4 +166,26 @@ xlmr_large = ModelMeta(
     public_training_code=None,
     public_training_data=None,
     training_datasets=set(),
+    citation="""@article{DBLP:journals/corr/abs-1911-02116,
+  author    = {Alexis Conneau and
+               Kartikay Khandelwal and
+               Naman Goyal and
+               Vishrav Chaudhary and
+               Guillaume Wenzek and
+               Francisco Guzm{\'{a}}n and
+               Edouard Grave and
+               Myle Ott and
+               Luke Zettlemoyer and
+               Veselin Stoyanov},
+  title     = {Unsupervised Cross-lingual Representation Learning at Scale},
+  journal   = {CoRR},
+  volume    = {abs/1911.02116},
+  year      = {2019},
+  url       = {http://arxiv.org/abs/1911.02116},
+  eprinttype = {arXiv},
+  eprint    = {1911.02116},
+  timestamp = {Mon, 11 Nov 2019 18:38:09 +0100},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-1911-02116.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}""",
 )

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",
+}""",
 )