@inproceedings{t-y-s-s-chowdhury-2025-fairness,
title = "Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal {NLP}",
author = "T.y.s.s, Santosh and
Chowdhury, Irtiza",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1188/",
doi = "10.18653/v1/2025.acl-long.1188",
pages = "24376--24390",
ISBN = "979-8-89176-251-0",
abstract = "Fairness in NLP must extend beyond performance parity to encompass equitable reliability across groups. This study exposes a criticalblind spot: models often make less reliable or overconfident predictions for marginalized groups, even when overall performance appearsfair. Using the FairLex benchmark as a case study in legal NLP, we systematically evaluate both performance and reliability dispari-ties across demographic, regional, and legal attributes spanning four jurisdictions. We show that domain-specific pre-training consistentlyimproves both performance and reliability, especially for underrepresented groups. However, common bias mitigation methods frequentlyworsen reliability disparities, revealing a trade-off not captured by performance metrics alone. Our results call for a rethinking of fairnessin high-stakes NLP: To ensure equitable treatment, models must not only be accurate, but also reliably self-aware across all groups."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="t-y-s-s-chowdhury-2025-fairness">
<titleInfo>
<title>Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.y.s.s</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irtiza</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Fairness in NLP must extend beyond performance parity to encompass equitable reliability across groups. This study exposes a criticalblind spot: models often make less reliable or overconfident predictions for marginalized groups, even when overall performance appearsfair. Using the FairLex benchmark as a case study in legal NLP, we systematically evaluate both performance and reliability dispari-ties across demographic, regional, and legal attributes spanning four jurisdictions. We show that domain-specific pre-training consistentlyimproves both performance and reliability, especially for underrepresented groups. However, common bias mitigation methods frequentlyworsen reliability disparities, revealing a trade-off not captured by performance metrics alone. Our results call for a rethinking of fairnessin high-stakes NLP: To ensure equitable treatment, models must not only be accurate, but also reliably self-aware across all groups.</abstract>
<identifier type="citekey">t-y-s-s-chowdhury-2025-fairness</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1188</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1188/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>24376</start>
<end>24390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal NLP
%A T.y.s.s, Santosh
%A Chowdhury, Irtiza
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F t-y-s-s-chowdhury-2025-fairness
%X Fairness in NLP must extend beyond performance parity to encompass equitable reliability across groups. This study exposes a criticalblind spot: models often make less reliable or overconfident predictions for marginalized groups, even when overall performance appearsfair. Using the FairLex benchmark as a case study in legal NLP, we systematically evaluate both performance and reliability dispari-ties across demographic, regional, and legal attributes spanning four jurisdictions. We show that domain-specific pre-training consistentlyimproves both performance and reliability, especially for underrepresented groups. However, common bias mitigation methods frequentlyworsen reliability disparities, revealing a trade-off not captured by performance metrics alone. Our results call for a rethinking of fairnessin high-stakes NLP: To ensure equitable treatment, models must not only be accurate, but also reliably self-aware across all groups.
%R 10.18653/v1/2025.acl-long.1188
%U https://aclanthology.org/2025.acl-long.1188/
%U https://doi.org/10.18653/v1/2025.acl-long.1188
%P 24376-24390
Markdown (Informal)
[Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal NLP](https://aclanthology.org/2025.acl-long.1188/) (T.y.s.s & Chowdhury, ACL 2025)
ACL