add all references

src/about.py

@@ -241,4 +241,190 @@ CITATION_BUTTON_TEXT = r"""
 	publisher    = {Hugging Face},
 	howpublished = "\url{https://huggingface.co/spaces/speakleash/open_pl_llm_leaderboard}"
 }
+
+@misc{eval-harness,
+  author       = {Gao, Leo and Tow, Jonathan and Abbasi, Baber and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and Le Noac'h, Alain and Li, Haonan and McDonell, Kyle and Muennighoff, Niklas and Ociepa, Chris and Phang, Jason and Reynolds, Laria and Schoelkopf, Hailey and Skowron, Aviya and Sutawika, Lintang and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy},
+  title        = {A framework for few-shot language model evaluation},
+  month        = 07,
+  year         = 2024,
+  publisher    = {Zenodo},
+  version      = {v0.4.3},
+  doi          = {10.5281/zenodo.12608602},
+  url          = {https://zenodo.org/records/12608602}
+}
+
+@book{przepiorkowski2012narodowy,
+title={Narodowy korpus j{\k{e}}zyka polskiego},
+author={Przepi{\'o}rkowski, Adam},
+year={2012},
+publisher={Naukowe PWN}
+}
+
+@inproceedings{kocon-etal-2019-multi,
+title = "Multi-Level Sentiment Analysis of {P}ol{E}mo 2.0: Extended Corpus of Multi-Domain Consumer Reviews",
+author = "Koco{\'n}, Jan and
+Mi{\l}kowski, Piotr and
+Za{\'s}ko-Zieli{\'n}ska, Monika",
+booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
+month = nov,
+year = "2019",
+address = "Hong Kong, China",
+publisher = "Association for Computational Linguistics",
+url = "https://www.aclweb.org/anthology/K19-1092",
+doi = "10.18653/v1/K19-1092",
+pages = "980--991",
+}
+
+@inproceedings{marcinczuk2013open,
+title={Open dataset for development of Polish Question Answering systems},
+author={Marcinczuk, Micha{\l} and Ptak, Marcin and Radziszewski, Adam and Piasecki, Maciej},
+booktitle={Proceedings of the 6th Language \& Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, Wydawnictwo Poznanskie, Fundacja Uniwersytetu im. Adama Mickiewicza},
+year={2013}
+}
+
+@inproceedings{ogro:kop:14:lrec,
+title={The {P}olish {S}ummaries {C}orpus},
+author={Ogrodniczuk, Maciej and Kope{\'c}, Mateusz},
+booktitle = "Proceedings of the Ninth International {C}onference on {L}anguage {R}esources and {E}valuation, {LREC}~2014",
+year = "2014",
+}
+
+@inproceedings{dadas-etal-2020-evaluation,
+  title = "Evaluation of Sentence Representations in {P}olish",
+  author = "Dadas, Slawomir  and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}",
+  booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
+  month = may,
+  year = "2020",
+  address = "Marseille, France",
+  publisher = "European Language Resources Association",
+  url = "https://aclanthology.org/2020.lrec-1.207",
+  pages = "1674--1680",
+  language = "English",
+  ISBN = "979-10-95546-34-4",
+}
+
+@inproceedings{9945218,
+  author={Dadas, S{\l}awomir},
+  booktitle={2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, 
+  title={Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases}, 
+  year={2022},
+  volume={},
+  number={},
+  pages={371-378},
+  doi={10.1109/SMC53654.2022.9945218}
+}
+
+@article{ptaszynski2023expert,
+  title={Expert-Annotated Dataset to Study Cyberbullying in Polish Language},
+  author={Ptaszynski, Michal and Pieciukiewicz, Agata and Dybala, Pawel and Skrzek, Pawel and Soliwoda, Kamil and Fortuna, Marcin and Leliwa, Gniewosz and Wroczynski, Michal},
+  journal={Data},
+  volume={9},
+  number={1},
+  pages={1},
+  year={2023},
+  publisher={MDPI}
+}
+
+@inproceedings{rybak-etal-2024-polqa-polish,
+    title = "{P}ol{QA}: {P}olish Question Answering Dataset",
+    author = "Rybak, Piotr  and
+      Przyby{\l}a, Piotr  and
+      Ogrodniczuk, Maciej",
+    editor = "Calzolari, Nicoletta  and
+      Kan, Min-Yen  and
+      Hoste, Veronique  and
+      Lenci, Alessandro  and
+      Sakti, Sakriani  and
+      Xue, Nianwen",
+    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
+    month = may,
+    year = "2024",
+    address = "Torino, Italia",
+    publisher = "ELRA and ICCL",
+    url = "https://aclanthology.org/2024.lrec-main.1125",
+    pages = "12846--12855",
+    abstract = "Recently proposed systems for open-domain question answering (OpenQA) require large amounts of training data to achieve state-of-the-art performance. However, data annotation is known to be time-consuming and therefore expensive to acquire. As a result, the appropriate datasets are available only for a handful of languages (mainly English and Chinese). In this work, we introduce and publicly release PolQA, the first Polish dataset for OpenQA. It consists of 7,000 questions, 87,525 manually labeled evidence passages, and a corpus of over 7,097,322 candidate passages. Each question is classified according to its formulation, type, as well as entity type of the answer. This resource allows us to evaluate the impact of different annotation choices on the performance of the QA system and propose an efficient annotation strategy that increases the passage retrieval accuracy@10 by 10.55 p.p. while reducing the annotation cost by 82{\%}.",
+}
+
+@inproceedings{tuora2023poquad,
+    title={PoQuAD-The Polish Question Answering Dataset-Description and Analysis},
+    author={Tuora, Ryszard and Zwierzchowska, Aleksandra and Zawadzka-Paluektau, Natalia and Klamra, Cezary and Kobyli{\'n}ski, {\L}ukasz},
+    booktitle={Proceedings of the 12th Knowledge Capture Conference 2023},
+    pages={105--113},
+    year={2023}
+}
+
+@inproceedings{bandarkar-etal-2024-belebele,
+    title = "The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants",
+    author = "Bandarkar, Lucas  and
+      Liang, Davis  and
+      Muller, Benjamin  and
+      Artetxe, Mikel  and
+      Shukla, Satya Narayan  and
+      Husa, Donald  and
+      Goyal, Naman  and
+      Krishnan, Abhinandan  and
+      Zettlemoyer, Luke  and
+      Khabsa, Madian",
+    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
+    month = aug,
+    year = "2024",
+    address = "Bangkok, Thailand and virtual meeting",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.acl-long.44",
+    pages = "749--775",
+}
+
+@misc{paech2024eqbenchemotionalintelligencebenchmark,
+      title={EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models}, 
+      author={Samuel J. Paech},
+      year={2024},
+      eprint={2312.06281},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2312.06281}, 
+}
+
+@misc{fwpes2024,
+  title={speakleash/PES-2018-2022},
+  author={Maria, Filipkowska and Krzyszof, Wróbel},
+  year={2024},
+  howpublished={\url{https://huggingface.co/datasets/speakleash/PES-2018-2022}},
+}
+
+@misc{pkgpes2024,
+  title={amu-cai/PES-2018-2022},
+  author={Jakub Pokrywka and Jeremi Kaczmarek and Edward Gorzelańczyk},
+  year={2024},
+  howpublished={\url{https://huggingface.co/datasets/amu-cai/PES-2018-2022}},
+}
+
+@misc{pokrywka2024gpt4,
+      title={GPT-4 passes most of the 297 written Polish Board Certification Examinations}, 
+      author={Jakub Pokrywka and Jeremi Kaczmarek and Edward Gorzelańczyk},
+      year={2024},
+      eprint={2405.01589},
+      archivePrefix={arXiv},
+      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
+}
+
+@inproceedings{rybak-etal-2020-klej,
+title = "{KLEJ}: Comprehensive Benchmark for Polish Language Understanding",
+author = "Rybak, Piotr and Mroczkowski, Robert and Tracz, Janusz and Gawlik, Ireneusz",
+booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
+month = jul,
+year = "2020",
+address = "Online",
+publisher = "Association for Computational Linguistics",
+url = "https://www.aclweb.org/anthology/2020.acl-main.111",
+pages = "1191--1201",
+}
+
+@misc{open-llm-leaderboard-v1,
+  author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
+  title = {Open LLM Leaderboard (2023-2024)},
+  year = {2023},
+  publisher = {Hugging Face},
+  howpublished = "\url{https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard}"
+}
 """