<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2025-distilling">
    <titleInfo>
        <title>Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinhyeong</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeongwan</namePart>
        <namePart type="family">Shin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seeun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seongdeok</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joungsu</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jongbae</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chun</namePart>
        <namePart type="given">Hwan</namePart>
        <namePart type="family">Jung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youjin</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saloni</namePart>
            <namePart type="family">Potdar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lina</namePart>
            <namePart type="family">Rojas-Barahona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastien</namePart>
            <namePart type="family">Montella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou (China)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-333-3</identifier>
    </relatedItem>
    <abstract>Retrieval-Augmented Generation (RAG) has shown strong performance in open-domain tasks, but its effectiveness in industrial domains is limited by a lack of domain understanding and document structural elements (DSE) such as tables, figures, charts, and formula.To address this challenge, we propose an efficient knowledge distillation framework that transfers complementary knowledge from both Large Language Models (LLMs) and Vision-Language Models (VLMs) into a compact domain-specific retriever.Extensive experiments and analysis on real-world industrial datasets from shipbuilding and electrical equipment domains demonstrate that the proposed framework improves both domain understanding and visual-structural retrieval, outperforming larger baselines while requiring significantly less computational complexity.</abstract>
    <identifier type="citekey">lim-etal-2025-distilling</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-industry.173/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>2551</start>
            <end>2563</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding
%A Lim, Jinhyeong
%A Shin, Jeongwan
%A Lee, Seeun
%A Kim, Seongdeok
%A Choi, Joungsu
%A Kim, Jongbae
%A Jung, Chun Hwan
%A Kang, Youjin
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F lim-etal-2025-distilling
%X Retrieval-Augmented Generation (RAG) has shown strong performance in open-domain tasks, but its effectiveness in industrial domains is limited by a lack of domain understanding and document structural elements (DSE) such as tables, figures, charts, and formula.To address this challenge, we propose an efficient knowledge distillation framework that transfers complementary knowledge from both Large Language Models (LLMs) and Vision-Language Models (VLMs) into a compact domain-specific retriever.Extensive experiments and analysis on real-world industrial datasets from shipbuilding and electrical equipment domains demonstrate that the proposed framework improves both domain understanding and visual-structural retrieval, outperforming larger baselines while requiring significantly less computational complexity.
%U https://aclanthology.org/2025.emnlp-industry.173/
%P 2551-2563

Markdown (Informal)

[Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding](https://aclanthology.org/2025.emnlp-industry.173/) (Lim et al., EMNLP 2025)

• Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding (Lim et al., EMNLP 2025)

ACL

• Jinhyeong Lim, Jeongwan Shin, Seeun Lee, Seongdeok Kim, Joungsu Choi, Jongbae Kim, Chun Hwan Jung, and Youjin Kang. 2025. Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2551–2563, Suzhou (China). Association for Computational Linguistics.