<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="satyadharma-etal-2026-positional">
    <titleInfo>
        <title>Positional task conditioning for scalable defect detection across product families in large product catalogs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soham</namePart>
        <namePart type="family">Satyadharma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gabriel</namePart>
        <namePart type="family">Roccabruna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Suleiman</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Khan</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Product families in large product catalogs suffer from inconsistencies such as duplicates and unit mismatches that degrade customer experience. Detecting these requires reasoning over multiple error types across lengthy product listings, where LLM classification quality degrades due to long-context limitations. We address this by decomposing detection into focused sub-tasks that reduce context and isolate error types, improving F1 from 52% to 87%. For scalable deployment, we introduce Positional Task Conditioning (PTC), which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries. PTC outperforms rationale-based distillation across five models and two architecture families, achieving within 1.79% F1 of the frontier at upto 98% lower cost. Our system is deployed across multiple countries processing 10+ million product families.</abstract>
    <identifier type="citekey">satyadharma-etal-2026-positional</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.192/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3226</start>
            <end>3239</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Positional task conditioning for scalable defect detection across product families in large product catalogs
%A Satyadharma, Soham
%A Roccabruna, Gabriel
%A Khan, Suleiman A.
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F satyadharma-etal-2026-positional
%X Product families in large product catalogs suffer from inconsistencies such as duplicates and unit mismatches that degrade customer experience. Detecting these requires reasoning over multiple error types across lengthy product listings, where LLM classification quality degrades due to long-context limitations. We address this by decomposing detection into focused sub-tasks that reduce context and isolate error types, improving F1 from 52% to 87%. For scalable deployment, we introduce Positional Task Conditioning (PTC), which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries. PTC outperforms rationale-based distillation across five models and two architecture families, achieving within 1.79% F1 of the frontier at upto 98% lower cost. Our system is deployed across multiple countries processing 10+ million product families.
%U https://aclanthology.org/2026.emnlp-industry.192/
%P 3226-3239

Markdown (Informal)

[Positional task conditioning for scalable defect detection across product families in large product catalogs](https://aclanthology.org/2026.emnlp-industry.192/) (Satyadharma et al., EMNLP 2026)

• Positional task conditioning for scalable defect detection across product families in large product catalogs (Satyadharma et al., EMNLP 2026)

ACL

• Soham Satyadharma, Gabriel Roccabruna, and Suleiman A. Khan. 2026. Positional task conditioning for scalable defect detection across product families in large product catalogs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3226–3239, Budapest, Hungary. Association for Computational Linguistics.