{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T01:23:58Z","timestamp":1767835438558,"version":"3.49.0"},"reference-count":16,"publisher":"Polish Information Processing Society","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.15439\/2025f6165","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:44:23Z","timestamp":1761119063000},"page":"111-119","source":"Crossref","is-referenced-by-count":1,"title":["Comparison of Large Language Models Supporting the Polish Language in Terms of Faithfulness in Retrieval-Augmented Generation Applications"],"prefix":"10.15439","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3336-4962","authenticated-orcid":true,"given":"Marcin","family":"Blachnik","sequence":"first","affiliation":[{"name":"Silesian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakub","family":"Chmielewski","sequence":"additional","affiliation":[{"name":"Silesian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6175","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","unstructured":"Z. Li, X. Xu, T. Shen, C. Xu, J.-C. Gu, Y. Lai, C. Tao, and\nS. Ma, \u201cLeveraging large language models for NLG evaluation:\nAdvances and challenges,\u201d in Proceedings of the 2024 Conference on\nEmpirical Methods in Natural Language Processing, Y. Al-Onaizan,\nM. Bansal, and Y.-N. Chen, Eds. Miami, Florida, USA: Association for\nComputational Linguistics, Nov. 2024. https:\/\/dx.doi.org\/10.18653\/v1\/2024.emnlp-main.896 pp. 16 028\u201316 045. [Online]. Available: https:\/\/aclanthology.org\/2024.emnlp-main.896\/","DOI":"10.18653\/v1\/2024.emnlp-main.896"},{"key":"ref2","unstructured":"Y. Kuratov, A. Bulatov, P. Anokhin, I. Rodkin, D. Sorokin, A. Sorokin,\nand M. Burtsev, \u201cBabilong: Testing the limits of llms with long context\nreasoning-in-a-haystack,\u201d Advances in Neural Information Processing\nSystems, vol. 37, pp. 106 519\u2013106 554, 2024."},{"key":"ref3","unstructured":"Z. Guo, R. Jin, C. Liu, Y. Huang, D. Shi, L. Yu, Y. Liu, J. Li, B. Xiong,\nD. Xiong et al., \u201cEvaluating large language models: A comprehensive\nsurvey,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2310.19736, 2023."},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Y. Chang, X. Wang, J. Wang, Y. Wu, L. Yang, K. Zhu, H. Chen, X. Yi,\nC. Wang, Y. Wang et al., \u201cA survey on evaluation of large language\nmodels,\u201d ACM transactions on intelligent systems and technology,\nvol. 15, no. 3, pp. 1\u201345, 2024.","DOI":"10.1145\/3641289"},{"key":"ref5","unstructured":"T. Hu and X.-H. Zhou, \u201cUnveiling llm evaluation focused on metrics:\nChallenges and solutions,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2404.09135, 2024."},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"N. Reimers and I. Gurevych, \u201cSentence-bert: Sentence embeddings using\nsiamese bert-networks,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/1908.10084, 2019.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref7","unstructured":"J. Gu, X. Jiang, Z. Shi, H. Tan, X. Zhai, C. Xu, W. Li, Y. Shen,\nS. Ma, H. Liu et al., \u201cA survey on llm-as-a-judge,\u201d arXiv preprint\nhttps:\/\/arxiv.org\/abs\/2411.15594, 2024."},{"key":"ref8","unstructured":"\u201cDeepeval,\u201d https:\/\/docs.confident-ai.com\/, 2024."},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"J. Saad-Falcon, O. Khattab, C. Potts, and M. Zaharia, \u201cAres: An\nautomated evaluation framework for retrieval-augmented generation\nsystems,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2311.09476, 2023.","DOI":"10.18653\/v1\/2024.naacl-long.20"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"H. Yu, A. Gan, K. Zhang, S. Tong, Q. Liu, and Z. Liu, \u201cEvaluation of\nretrieval-augmented generation: A survey,\u201d in CCF Conference on Big\nData. Springer, 2024, pp. 102\u2013120.","DOI":"10.1007\/978-981-96-1024-2_8"},{"key":"ref11","unstructured":"Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun,\nH. Wang, and H. Wang, \u201cRetrieval-augmented generation for large\nlanguage models: A survey,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2312.10997, vol. 2,\nno. 1, 2023."},{"key":"ref12","unstructured":"J.-C. Gu, H.-X. Xu, J.-Y. Ma, P. Lu, Z.-H. Ling, K.-W. Chang, and\nN. Peng, \u201cModel editing harms general abilities of large language\nmodels: Regularization to the rescue,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2401.04700,\n2024."},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"W. Yang, F. Sun, X. Ma, X. Liu, D. Yin, and X. Cheng, \u201cThe butterfly\neffect of model editing: Few edits can trigger large language models\ncollapse,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2402.09656, 2024.","DOI":"10.18653\/v1\/2024.findings-acl.322"},{"key":"ref14","unstructured":"S. Sonkar, N. Liu, and R. G. Baraniuk, \u201cRegressive side effects of\ntraining language models to mimic student misconceptions,\u201d arXiv e-prints, pp. arXiv\u20132404, 2024."},{"key":"ref15","unstructured":"R. Rafailov, A. Sharma, E. Mitchell, C. D. Manning, S. Ermon, and\nC. Finn, \u201cDirect preference optimization: Your language model is\nsecretly a reward model,\u201d Advances in Neural Information Processing\nSystems, vol. 36, pp. 53 728\u201353 741, 2023."},{"key":"ref16","unstructured":"A. Arditi, O. Obeso, A. Syed, D. Paleka, N. Panickssery, W. Gurnee,\nand N. Nanda, \u201cRefusal in language models is mediated by a single\ndirection,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2406.11717, 2024."}],"event":{"name":"20th Conference on Computer Science and Intelligence Systems (FedCSIS)","theme":"Computer Science and Intelligence Systems","location":"Krak\u00f3w, Poland","acronym":"FedCSIS","number":"20","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["Annals of Computer Science and Information Systems","Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:45:52Z","timestamp":1761119152000},"score":1,"resource":{"primary":{"URL":"https:\/\/annals-csis.org\/Volume_43\/drp\/6165.html"}},"subtitle":[],"proceedings-subject":"Computer Science and Information Systems","short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":16,"URL":"https:\/\/doi.org\/10.15439\/2025f6165","relation":{},"ISSN":["2300-5963"],"issn-type":[{"value":"2300-5963","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}