<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-2026-bankshield">
    <titleInfo>
        <title>BankShield: Fairness-Aware Safety Guardrails for Indian-Language Banking AI</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Piyush</namePart>
        <namePart type="family">Agarwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>Safety guards for Indian-language banking must detect discrimination without changing verdicts solely because a demographic identity changes. We introduce GuardAudit, an evaluation protocol combining decontamination, paired harmful/benign calibration, counterfactual identity tests, and deployed-action evaluation, plus two released banking benchmarks. Across six guards, the hardest matched test remains unresolved: the best system flags a coded proxy denial while clearing its matched actuarial control on only 37.5% of pairs. BankShield, used as a case study, reaches 20.0% and false-flags 75.0% of expert-validated legitimate controls. On separate BharatBBQ subsets, it achieves 0% flip on benign identity substitutions and 66.7% biased-content catch; these disjoint measurements do not establish joint per-example fairness. Its unadapted 12B backbone supplies near-invariance and attack recall, while adaptation and a discrimination probe raise biased-content catch from 24% to 43% and 66.7%, not significantly above a smaller Indic guard’s 56.9% (p=0.09). Detection also falls from 81.6% in English to 42.6% in Devanagari Hindi. BankShield is therefore a diagnostic case study, not a deployment-ready fairness solution. We release the protocol, benchmarks, and frozen predictions.</abstract>
    <identifier type="citekey">agarwal-2026-bankshield</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.21/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>243</start>
            <end>262</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BankShield: Fairness-Aware Safety Guardrails for Indian-Language Banking AI
%A Agarwal, Piyush
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F agarwal-2026-bankshield
%X Safety guards for Indian-language banking must detect discrimination without changing verdicts solely because a demographic identity changes. We introduce GuardAudit, an evaluation protocol combining decontamination, paired harmful/benign calibration, counterfactual identity tests, and deployed-action evaluation, plus two released banking benchmarks. Across six guards, the hardest matched test remains unresolved: the best system flags a coded proxy denial while clearing its matched actuarial control on only 37.5% of pairs. BankShield, used as a case study, reaches 20.0% and false-flags 75.0% of expert-validated legitimate controls. On separate BharatBBQ subsets, it achieves 0% flip on benign identity substitutions and 66.7% biased-content catch; these disjoint measurements do not establish joint per-example fairness. Its unadapted 12B backbone supplies near-invariance and attack recall, while adaptation and a discrimination probe raise biased-content catch from 24% to 43% and 66.7%, not significantly above a smaller Indic guard’s 56.9% (p=0.09). Detection also falls from 81.6% in English to 42.6% in Devanagari Hindi. BankShield is therefore a diagnostic case study, not a deployment-ready fairness solution. We release the protocol, benchmarks, and frozen predictions.
%U https://aclanthology.org/2026.finnlp-1.21/
%P 243-262

Markdown (Informal)

[BankShield: Fairness-Aware Safety Guardrails for Indian-Language Banking AI](https://aclanthology.org/2026.finnlp-1.21/) (Agarwal, FinNLP 2026)

• BankShield: Fairness-Aware Safety Guardrails for Indian-Language Banking AI (Agarwal, FinNLP 2026)

ACL

• Piyush Agarwal. 2026. BankShield: Fairness-Aware Safety Guardrails for Indian-Language Banking AI. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 243–262, Budapest, Hungary. Association for Computational Linguistics.