<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolasani-dezaki-2026-progressive">
    <titleInfo>
        <title>Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lakshman</namePart>
        <namePart type="family">Kolasani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fatemeh</namePart>
        <namePart type="given">Taheri</namePart>
        <namePart type="family">Dezaki</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">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) excel at structured information generation but face cost and latency challenges when deployed at scale in user-facing products. We present a parameter efficient supervised fine-tuning pipeline for adapting a small language model (SLM) to structured attribute generation in e-commerce product listing, enabling continuous model improvement with implicit user feedback without expensive manual annotation. Our approach involves completeness-deficit guided curation, which ranks samples by divergence between model predictions and catalog listing attributes, selecting the highest completeness gap examples for progressive fine-tuning. Our system is deployed on a large-scale product listing service, reducing inference costs by 98% and p90 latency by 70% using a fine-tuned SLM relative to the baseline LLM while preserving an 86.4% user acceptance rate, translating to significant monthly infrastructure savings.</abstract>
    <identifier type="citekey">kolasani-dezaki-2026-progressive</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.40/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>585</start>
            <end>591</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce
%A Kolasani, Lakshman
%A Dezaki, Fatemeh Taheri
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%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, USA
%@ 979-8-89176-394-4
%F kolasani-dezaki-2026-progressive
%X Large language models (LLMs) excel at structured information generation but face cost and latency challenges when deployed at scale in user-facing products. We present a parameter efficient supervised fine-tuning pipeline for adapting a small language model (SLM) to structured attribute generation in e-commerce product listing, enabling continuous model improvement with implicit user feedback without expensive manual annotation. Our approach involves completeness-deficit guided curation, which ranks samples by divergence between model predictions and catalog listing attributes, selecting the highest completeness gap examples for progressive fine-tuning. Our system is deployed on a large-scale product listing service, reducing inference costs by 98% and p90 latency by 70% using a fine-tuned SLM relative to the baseline LLM while preserving an 86.4% user acceptance rate, translating to significant monthly infrastructure savings.
%U https://aclanthology.org/2026.acl-industry.40/
%P 585-591

Markdown (Informal)

[Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce](https://aclanthology.org/2026.acl-industry.40/) (Kolasani & Dezaki, ACL 2026)

• Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce (Kolasani & Dezaki, ACL 2026)

ACL

• Lakshman Kolasani and Fatemeh Taheri Dezaki. 2026. Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 585–591, San Diego, California, USA. Association for Computational Linguistics.