<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aditya-hari-etal-2026-right">
    <titleInfo>
        <title>Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kancharla</namePart>
        <namePart type="family">Aditya Hari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sai</namePart>
        <namePart type="family">Khadloya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arghya</namePart>
        <namePart type="family">Bhattacharya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kumarmanas</namePart>
        <namePart type="family">Nethil</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 Natural Legal Language Processing Workshop 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nikolaos</namePart>
            <namePart type="family">Aletras</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ilias</namePart>
            <namePart type="family">Chalkidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leslie</namePart>
            <namePart type="family">Barrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Cătălina</namePart>
            <namePart type="family">Goanță</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoțiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gerasimos</namePart>
            <namePart type="family">Spanakis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shanshan</namePart>
            <namePart type="family">Xu</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">979-8-89176-494-1</identifier>
    </relatedItem>
    <abstract>Several high-stakes administrative tasks require supporting verdicts and decisions with auditable reasoning. While the application of LLMs in this regard has been studied, existing benchmarks are unsuitable because they either score only the final answer or evaluate citation quality separately from outcome correctness. We introduce HS-BENCH, a benchmark for customs classification, to study this problem. The task involves assigning tariff codes to products with reasoning grounded in legal authorities. HS-BENCH consists of 1,390 product descriptions paired with supporting legal authorities across diverse sources, including dictionary definitions, statutory notes, and prior rulings. We propose Strict Support Accuracy (SSA), a metric that credits a prediction only when both the outcome and the reasoning are well supported. Evaluating frontier models in closed-book and oracle-evidence regimes, we find that classification accuracy and SSA diverge sharply: models often reach the correct outcome through incorrect reasoning. We release the dataset, extraction pipeline, and evaluation code at https://github.com/adalat-ai-tech/hs-bench to support research on auditable LLM systems in administrative law.</abstract>
    <identifier type="citekey">aditya-hari-etal-2026-right</identifier>
    <location>
        <url>https://aclanthology.org/2026.nllp-1.49/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>628</start>
            <end>639</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification
%A Aditya Hari, Kancharla
%A Khadloya, Sai
%A Bhattacharya, Arghya
%A Nethil, Kumarmanas
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F aditya-hari-etal-2026-right
%X Several high-stakes administrative tasks require supporting verdicts and decisions with auditable reasoning. While the application of LLMs in this regard has been studied, existing benchmarks are unsuitable because they either score only the final answer or evaluate citation quality separately from outcome correctness. We introduce HS-BENCH, a benchmark for customs classification, to study this problem. The task involves assigning tariff codes to products with reasoning grounded in legal authorities. HS-BENCH consists of 1,390 product descriptions paired with supporting legal authorities across diverse sources, including dictionary definitions, statutory notes, and prior rulings. We propose Strict Support Accuracy (SSA), a metric that credits a prediction only when both the outcome and the reasoning are well supported. Evaluating frontier models in closed-book and oracle-evidence regimes, we find that classification accuracy and SSA diverge sharply: models often reach the correct outcome through incorrect reasoning. We release the dataset, extraction pipeline, and evaluation code at https://github.com/adalat-ai-tech/hs-bench to support research on auditable LLM systems in administrative law.
%U https://aclanthology.org/2026.nllp-1.49/
%P 628-639

Markdown (Informal)

[Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification](https://aclanthology.org/2026.nllp-1.49/) (Aditya Hari et al., NLLP 2026)

• Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification (Aditya Hari et al., NLLP 2026)

ACL

• Kancharla Aditya Hari, Sai Khadloya, Arghya Bhattacharya, and Kumarmanas Nethil. 2026. Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification. In Proceedings of the Natural Legal Language Processing Workshop 2026, pages 628–639, Budapest, Hungary. Association for Computational Linguistics.