@inproceedings{wu-etal-2025-rag,
title = "Does {RAG} Introduce Unfairness in {LLM}s? Evaluating Fairness in Retrieval-Augmented Generation Systems",
author = "Wu, Xuyang and
Li, Shuowei and
Wu, Hsin-Tai and
Tao, Zhiqiang and
Fang, Yi",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.669/",
pages = "10021--10036",
abstract = "Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods poses challenges in identifying and mitigating biases, as each component is optimized for distinct objectives. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG, using scenario-based questions and analyzing disparities across demographic attributes. Our experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages. These findings underscore the need for targeted interventions to address fairness concerns throughout the RAG pipeline. The dataset and code used in this study are publicly available at this GitHub Repository."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2025-rag">
<titleInfo>
<title>Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuyang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuowei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Tai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods poses challenges in identifying and mitigating biases, as each component is optimized for distinct objectives. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG, using scenario-based questions and analyzing disparities across demographic attributes. Our experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages. These findings underscore the need for targeted interventions to address fairness concerns throughout the RAG pipeline. The dataset and code used in this study are publicly available at this GitHub Repository.</abstract>
<identifier type="citekey">wu-etal-2025-rag</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.669/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10021</start>
<end>10036</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
%A Wu, Xuyang
%A Li, Shuowei
%A Wu, Hsin-Tai
%A Tao, Zhiqiang
%A Fang, Yi
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F wu-etal-2025-rag
%X Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods poses challenges in identifying and mitigating biases, as each component is optimized for distinct objectives. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG, using scenario-based questions and analyzing disparities across demographic attributes. Our experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages. These findings underscore the need for targeted interventions to address fairness concerns throughout the RAG pipeline. The dataset and code used in this study are publicly available at this GitHub Repository.
%U https://aclanthology.org/2025.coling-main.669/
%P 10021-10036
Markdown (Informal)
[Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems](https://aclanthology.org/2025.coling-main.669/) (Wu et al., COLING 2025)
ACL