@inproceedings{grigoreva-etal-2024-rubia-russian,
title = "{R}u{B}ia: A {R}ussian Language Bias Detection Dataset",
author = "Grigoreva, Veronika and
Ivanova, Anastasiia and
Alimova, Ilseyar and
Artemova, Ekaterina",
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.1240",
pages = "14227--14239",
abstract = "Warning: this work contains upsetting or disturbing content. Large language models (LLMs) tend to learn the social and cultural biases present in the raw pre-training data. To test if an LLM{'}s behavior is fair, functional datasets are employed, and due to their purpose, these datasets are highly language and culture-specific. In this paper, we address a gap in the scope of multilingual bias evaluation by presenting a bias detection dataset specifically designed for the Russian language, dubbed as RuBia. The RuBia dataset is divided into 4 domains: gender, nationality, socio-economic status, and diverse, each of the domains is further divided into multiple fine-grained subdomains. Every example in the dataset consists of two sentences with the first reinforcing a potentially harmful stereotype or trope and the second contradicting it. These sentence pairs were first written by volunteers and then validated by native-speaking crowdsourcing workers. Overall, there are nearly 2,000 unique sentence pairs spread over 19 subdomains in RuBia. To illustrate the dataset{'}s purpose, we conduct a diagnostic evaluation of state-of-the-art or near-state-of-the-art LLMs and discuss the LLMs{'} predisposition to social biases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grigoreva-etal-2024-rubia-russian">
<titleInfo>
<title>RuBia: A Russian Language Bias Detection Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Grigoreva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Ivanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Warning: this work contains upsetting or disturbing content. Large language models (LLMs) tend to learn the social and cultural biases present in the raw pre-training data. To test if an LLM’s behavior is fair, functional datasets are employed, and due to their purpose, these datasets are highly language and culture-specific. In this paper, we address a gap in the scope of multilingual bias evaluation by presenting a bias detection dataset specifically designed for the Russian language, dubbed as RuBia. The RuBia dataset is divided into 4 domains: gender, nationality, socio-economic status, and diverse, each of the domains is further divided into multiple fine-grained subdomains. Every example in the dataset consists of two sentences with the first reinforcing a potentially harmful stereotype or trope and the second contradicting it. These sentence pairs were first written by volunteers and then validated by native-speaking crowdsourcing workers. Overall, there are nearly 2,000 unique sentence pairs spread over 19 subdomains in RuBia. To illustrate the dataset’s purpose, we conduct a diagnostic evaluation of state-of-the-art or near-state-of-the-art LLMs and discuss the LLMs’ predisposition to social biases.</abstract>
<identifier type="citekey">grigoreva-etal-2024-rubia-russian</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1240</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14227</start>
<end>14239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RuBia: A Russian Language Bias Detection Dataset
%A Grigoreva, Veronika
%A Ivanova, Anastasiia
%A Alimova, Ilseyar
%A Artemova, Ekaterina
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F grigoreva-etal-2024-rubia-russian
%X Warning: this work contains upsetting or disturbing content. Large language models (LLMs) tend to learn the social and cultural biases present in the raw pre-training data. To test if an LLM’s behavior is fair, functional datasets are employed, and due to their purpose, these datasets are highly language and culture-specific. In this paper, we address a gap in the scope of multilingual bias evaluation by presenting a bias detection dataset specifically designed for the Russian language, dubbed as RuBia. The RuBia dataset is divided into 4 domains: gender, nationality, socio-economic status, and diverse, each of the domains is further divided into multiple fine-grained subdomains. Every example in the dataset consists of two sentences with the first reinforcing a potentially harmful stereotype or trope and the second contradicting it. These sentence pairs were first written by volunteers and then validated by native-speaking crowdsourcing workers. Overall, there are nearly 2,000 unique sentence pairs spread over 19 subdomains in RuBia. To illustrate the dataset’s purpose, we conduct a diagnostic evaluation of state-of-the-art or near-state-of-the-art LLMs and discuss the LLMs’ predisposition to social biases.
%U https://aclanthology.org/2024.lrec-main.1240
%P 14227-14239
Markdown (Informal)
[RuBia: A Russian Language Bias Detection Dataset](https://aclanthology.org/2024.lrec-main.1240) (Grigoreva et al., LREC-COLING 2024)
ACL
- Veronika Grigoreva, Anastasiia Ivanova, Ilseyar Alimova, and Ekaterina Artemova. 2024. RuBia: A Russian Language Bias Detection Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14227–14239, Torino, Italia. ELRA and ICCL.