@inproceedings{zhou-etal-2022-vlstereoset,
title = "{VLS}tereo{S}et: A Study of Stereotypical Bias in Pre-trained Vision-Language Models",
author = "Zhou, Kankan and
Lai, Eason and
Jiang, Jing",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.40/",
doi = "10.18653/v1/2022.aacl-main.40",
pages = "527--538",
abstract = "In this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, and extend it into a vision-language probing dataset called VLStereoSet to measure stereotypical bias in vision-language models. We analyze the differences between text and image and propose a probing task that detects bias by evaluating a model`s tendency to pick stereotypical statements as captions for anti-stereotypical images. We further define several metrics to measure both a vision-language model`s overall stereotypical bias and its intra-modal and inter-modal bias. Experiments on six representative pre-trained vision-language models demonstrate that stereotypical biases clearly exist in most of these models and across all four bias categories, with gender bias slightly more evident. Further analysis using gender bias data and two vision-language models also suggest that both intra-modal and inter-modal bias exist."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2022-vlstereoset">
<titleInfo>
<title>VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kankan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eason</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, and extend it into a vision-language probing dataset called VLStereoSet to measure stereotypical bias in vision-language models. We analyze the differences between text and image and propose a probing task that detects bias by evaluating a model‘s tendency to pick stereotypical statements as captions for anti-stereotypical images. We further define several metrics to measure both a vision-language model‘s overall stereotypical bias and its intra-modal and inter-modal bias. Experiments on six representative pre-trained vision-language models demonstrate that stereotypical biases clearly exist in most of these models and across all four bias categories, with gender bias slightly more evident. Further analysis using gender bias data and two vision-language models also suggest that both intra-modal and inter-modal bias exist.</abstract>
<identifier type="citekey">zhou-etal-2022-vlstereoset</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-main.40</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.40/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>527</start>
<end>538</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models
%A Zhou, Kankan
%A Lai, Eason
%A Jiang, Jing
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F zhou-etal-2022-vlstereoset
%X In this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, and extend it into a vision-language probing dataset called VLStereoSet to measure stereotypical bias in vision-language models. We analyze the differences between text and image and propose a probing task that detects bias by evaluating a model‘s tendency to pick stereotypical statements as captions for anti-stereotypical images. We further define several metrics to measure both a vision-language model‘s overall stereotypical bias and its intra-modal and inter-modal bias. Experiments on six representative pre-trained vision-language models demonstrate that stereotypical biases clearly exist in most of these models and across all four bias categories, with gender bias slightly more evident. Further analysis using gender bias data and two vision-language models also suggest that both intra-modal and inter-modal bias exist.
%R 10.18653/v1/2022.aacl-main.40
%U https://aclanthology.org/2022.aacl-main.40/
%U https://doi.org/10.18653/v1/2022.aacl-main.40
%P 527-538
Markdown (Informal)
[VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models](https://aclanthology.org/2022.aacl-main.40/) (Zhou et al., AACL-IJCNLP 2022)
ACL
- Kankan Zhou, Eason Lai, and Jing Jiang. 2022. VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 527–538, Online only. Association for Computational Linguistics.