@inproceedings{CaporussoEtAl2026LREC,
  title="Exploring Social Bias in {S}lovenia: The {EEC-SL} Dataset",
  author = "Caporusso, Jaya  and
    Hoogland, Damar  and
    Koloski, Boshko  and
    Purver, Matthew  and
    Pollak, Senja and 
    Vintar, {\v{S}}pela",
  year=2026,
  month=may,
  booktitle = {Proceedings of the 15th Language Resources and Evaluation Conference (LREC 2026)},
  location = "Palma, Mallorca, Spain",
  pages = {4019--4030},
  doi = {10.63317/2pdt2x4ci6e5},
  url={https://doi.org/10.63317/2pdt2x4ci6e5}, 
  url={https://lrec.elra.info/lrec2026-main-318}, 
  publisher = {European Language Resources Association (ELRA)},
  editor = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},
  abstract = {We introduce the EEC-SL dataset, an adaptation of the Equity Evaluation Corpus from English to Slovenian. Based on 11 sentence templates, the dataset contains 8,640 sentences, including pairs of minimally-distant sentences, varying with regard to one of two variables: gender (female or male), and ethnicity (Slovenian or not-Slovenian). In order to validate our selection of personal names, we create a localised version of the Implicit Association Test for ethnic bias, in which participants show a significant implicit bias favouring Slovenian over non-Slovenian names. We use the dataset to evaluate social bias in three computational language models (large language models and an encoder-only transformer) to perform sentiment analysis—specifically, valence. We analyse the results in terms of differences in sentiment between minimally-distant groups of sentences and inferential tests. We found limited evidence for social bias with regard to ethnicity, and no evidence for gender bias, in any of the employed models.}
}