@inproceedings{caporusso-etal-2026-exploring,
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, Spela",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.318/",
doi = "10.63317/2pdt2x4ci6e5",
pages = "4019--4030",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="caporusso-etal-2026-exploring">
<titleInfo>
<title>Exploring Social Bias in Slovenia: The EEC-SL Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaya</namePart>
<namePart type="family">Caporusso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damar</namePart>
<namePart type="family">Hoogland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boshko</namePart>
<namePart type="family">Koloski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spela</namePart>
<namePart type="family">Vintar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">caporusso-etal-2026-exploring</identifier>
<identifier type="doi">10.63317/2pdt2x4ci6e5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.318/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4019</start>
<end>4030</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Social Bias in Slovenia: The EEC-SL Dataset
%A Caporusso, Jaya
%A Hoogland, Damar
%A Koloski, Boshko
%A Purver, Matthew
%A Pollak, Senja
%A Vintar, Spela
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F caporusso-etal-2026-exploring
%X 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.
%R 10.63317/2pdt2x4ci6e5
%U https://aclanthology.org/2026.lrec-1.318/
%U https://doi.org/10.63317/2pdt2x4ci6e5
%P 4019-4030
Markdown (Informal)
[Exploring Social Bias in Slovenia: The EEC-SL Dataset](https://aclanthology.org/2026.lrec-1.318/) (Caporusso et al., LREC 2026)
ACL
- Jaya Caporusso, Damar Hoogland, Boshko Koloski, Matthew Purver, Senja Pollak, and Spela Vintar. 2026. Exploring Social Bias in Slovenia: The EEC-SL Dataset. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4019–4030, Palma de Mallorca, Spain. ELRA Language Resource Association.