@inproceedings{liu-etal-2023-uncovering,
title = "Uncovering and Categorizing Social Biases in Text-to-{SQL}",
author = "Liu, Yan and
Gao, Yan and
Su, Zhe and
Chen, Xiaokang and
Ash, Elliott and
Lou, Jian-Guang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.759",
doi = "10.18653/v1/2023.acl-long.759",
pages = "13573--13584",
abstract = "Large pre-trained language models are acknowledged to carry social bias towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and mitigate social bias in Text-to-SQL models. We summarize the categories of social bias that may occur in structural data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social bias at very different rates. We show how to take advantage of our methodology to assess and mitigate social bias in the downstream Text-to-SQL task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-uncovering">
<titleInfo>
<title>Uncovering and Categorizing Social Biases in Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaokang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elliott</namePart>
<namePart type="family">Ash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian-Guang</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large pre-trained language models are acknowledged to carry social bias towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and mitigate social bias in Text-to-SQL models. We summarize the categories of social bias that may occur in structural data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social bias at very different rates. We show how to take advantage of our methodology to assess and mitigate social bias in the downstream Text-to-SQL task.</abstract>
<identifier type="citekey">liu-etal-2023-uncovering</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.759</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.759</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13573</start>
<end>13584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncovering and Categorizing Social Biases in Text-to-SQL
%A Liu, Yan
%A Gao, Yan
%A Su, Zhe
%A Chen, Xiaokang
%A Ash, Elliott
%A Lou, Jian-Guang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-uncovering
%X Large pre-trained language models are acknowledged to carry social bias towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and mitigate social bias in Text-to-SQL models. We summarize the categories of social bias that may occur in structural data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social bias at very different rates. We show how to take advantage of our methodology to assess and mitigate social bias in the downstream Text-to-SQL task.
%R 10.18653/v1/2023.acl-long.759
%U https://aclanthology.org/2023.acl-long.759
%U https://doi.org/10.18653/v1/2023.acl-long.759
%P 13573-13584
Markdown (Informal)
[Uncovering and Categorizing Social Biases in Text-to-SQL](https://aclanthology.org/2023.acl-long.759) (Liu et al., ACL 2023)
ACL
- Yan Liu, Yan Gao, Zhe Su, Xiaokang Chen, Elliott Ash, and Jian-Guang Lou. 2023. Uncovering and Categorizing Social Biases in Text-to-SQL. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13573–13584, Toronto, Canada. Association for Computational Linguistics.