@inproceedings{dutta-2026-thesis,
title = "Thesis Proposal: Auditing and Mitigating Demographic Bias in Multi-Stage Retrieval Systems for Criminal Justice Applications",
author = "Dutta, Archan",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.97/",
pages = "1115--1124",
ISBN = "979-8-89176-393-7",
abstract = "We propose a comprehensive research agenda to detect, measure, and mitigate racial bias in Natural Language Processing (NLP) systems deployed in criminal justice contexts. Our preliminary work demonstrates that racial descriptors systematically alter embedding similarity scores and retrieval rankings across six models, with bias being race-specific and models showing rank displacements of 1.82 to 7.44 positions, on average. This empirically indicates that even small shifts in similarity scores can displace relevant records outside top-10 results, leading to systematic under-retrieval of records involving certain demographic groups.Building on these findings, this thesis proposes four research questions: (1) developing and evaluating debiasing techniques including counterfactual data augmentation, adversarial training, and fairness-constrained fine-tuning; (2) validating synthetic findings on authentic law enforcement data through IRB-approved partnerships; (3) investigating intersectional bias patterns across race, gender, and age; and (4) we extend beyond embedding-level analysis to examine how bias propagates across modern multi-stage retrieval pipelines from embeddings to cross-encoders to LLMs. Expected contributions include empirical comparisons of debiasing methods, bias benchmarks for criminal justice NLP, deployment guidelines for fairness-aware retrieval systems, and the first comprehensive analysis of multi-stage bias propagation in retrieval pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dutta-2026-thesis">
<titleInfo>
<title>Thesis Proposal: Auditing and Mitigating Demographic Bias in Multi-Stage Retrieval Systems for Criminal Justice Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archan</namePart>
<namePart type="family">Dutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>We propose a comprehensive research agenda to detect, measure, and mitigate racial bias in Natural Language Processing (NLP) systems deployed in criminal justice contexts. Our preliminary work demonstrates that racial descriptors systematically alter embedding similarity scores and retrieval rankings across six models, with bias being race-specific and models showing rank displacements of 1.82 to 7.44 positions, on average. This empirically indicates that even small shifts in similarity scores can displace relevant records outside top-10 results, leading to systematic under-retrieval of records involving certain demographic groups.Building on these findings, this thesis proposes four research questions: (1) developing and evaluating debiasing techniques including counterfactual data augmentation, adversarial training, and fairness-constrained fine-tuning; (2) validating synthetic findings on authentic law enforcement data through IRB-approved partnerships; (3) investigating intersectional bias patterns across race, gender, and age; and (4) we extend beyond embedding-level analysis to examine how bias propagates across modern multi-stage retrieval pipelines from embeddings to cross-encoders to LLMs. Expected contributions include empirical comparisons of debiasing methods, bias benchmarks for criminal justice NLP, deployment guidelines for fairness-aware retrieval systems, and the first comprehensive analysis of multi-stage bias propagation in retrieval pipelines.</abstract>
<identifier type="citekey">dutta-2026-thesis</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.97/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1115</start>
<end>1124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thesis Proposal: Auditing and Mitigating Demographic Bias in Multi-Stage Retrieval Systems for Criminal Justice Applications
%A Dutta, Archan
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F dutta-2026-thesis
%X We propose a comprehensive research agenda to detect, measure, and mitigate racial bias in Natural Language Processing (NLP) systems deployed in criminal justice contexts. Our preliminary work demonstrates that racial descriptors systematically alter embedding similarity scores and retrieval rankings across six models, with bias being race-specific and models showing rank displacements of 1.82 to 7.44 positions, on average. This empirically indicates that even small shifts in similarity scores can displace relevant records outside top-10 results, leading to systematic under-retrieval of records involving certain demographic groups.Building on these findings, this thesis proposes four research questions: (1) developing and evaluating debiasing techniques including counterfactual data augmentation, adversarial training, and fairness-constrained fine-tuning; (2) validating synthetic findings on authentic law enforcement data through IRB-approved partnerships; (3) investigating intersectional bias patterns across race, gender, and age; and (4) we extend beyond embedding-level analysis to examine how bias propagates across modern multi-stage retrieval pipelines from embeddings to cross-encoders to LLMs. Expected contributions include empirical comparisons of debiasing methods, bias benchmarks for criminal justice NLP, deployment guidelines for fairness-aware retrieval systems, and the first comprehensive analysis of multi-stage bias propagation in retrieval pipelines.
%U https://aclanthology.org/2026.acl-srw.97/
%P 1115-1124
Markdown (Informal)
[Thesis Proposal: Auditing and Mitigating Demographic Bias in Multi-Stage Retrieval Systems for Criminal Justice Applications](https://aclanthology.org/2026.acl-srw.97/) (Dutta, ACL 2026)
ACL