@inproceedings{po-swiata-etal-2026-pl,
    title = "{PL}-{MTEB}: {P}olish Massive Text Embedding Benchmark",
    author = "Po{\textbackslash}'swiata, Rafa{\{}{\textbackslash}l{\}}  and
      Dadas, S{\{}{\textbackslash}l{\}}awomir  and
      Pere{\{}{\textbackslash}l{\}}kiewicz, Micha{\{}{\textbackslash}l{\}} Wiktor",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1773/",
    pages = "35601--35619",
    ISBN = "979-8-89176-395-1",
    abstract = "In this paper, we introduce the Polish Massive Text Embedding Benchmark (PL-MTEB), a comprehensive benchmark for text embeddings in the Polish language. PL-MTEB comprises 30 diverse NLP tasks across five categories: classification, clustering, pair classification, information retrieval, and semantic text similarity. Within the scope of this work, we added 12 new Polish-language tasks to MTEB based on existing datasets and prepared two new datasets used to create four clustering tasks. We evaluated 30 publicly available text embedding models, including Polish and multilingual models. We analyzed the results in detail for specific task types and model sizes. We made the prepared datasets, the source code for evaluation, and the obtained results available to the public at https://github.com/rafalposwiata/pl-mteb."
}