@inproceedings{ling-etal-2025-captions,
title = "Captions Speak Louder than Images: Generalizing Foundation Models for {E}-commerce from High-quality Multimodal Instruction Data",
author = "Ling, Xinyi and
Du, Hanwen and
Peng, Bo and
Zhu, Zhihui and
Ning, Xia",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.42/",
pages = "743--768",
ISBN = "979-8-89176-298-5",
abstract = "Multimodal foundation models (MFMs) have demonstrated strong capabilities in e-commerce by effectively leveraging multimodal data to enhance product understanding and user experienceHowever, the development of e-commerce MFMs is hindered by two challenges: (1) the scarcity of large-scale, high-quality multimodal benchmark datasets; and (2) the lack of effective multimodal information integration methods in e-commerce. To address these challenges, we introduce MMECInstruct, the first large-scale, high-quality multimodal instruction dataset designed specifically for e-commerce MFMs. MMECInstruct comprises 75,000 samples covering 7 real-world e-commerce tasks, supporting both in-domain (IND) and out-of-domain (OOD) evaluations. Leveraging MMECInstruct, we develop CASLIE, a lightweight framework that enhances multimodal information understanding and integration for e-commerce. Our comprehensive evaluation demonstrates that MMECInstruct endows CASLIE with advanced capability and strong generalizability in e-commerce applications. MMECInstruct and CASLIE models are publicly accessible through https://github.com/ninglab/CASLIE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ling-etal-2025-captions">
<titleInfo>
<title>Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanwen</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Multimodal foundation models (MFMs) have demonstrated strong capabilities in e-commerce by effectively leveraging multimodal data to enhance product understanding and user experienceHowever, the development of e-commerce MFMs is hindered by two challenges: (1) the scarcity of large-scale, high-quality multimodal benchmark datasets; and (2) the lack of effective multimodal information integration methods in e-commerce. To address these challenges, we introduce MMECInstruct, the first large-scale, high-quality multimodal instruction dataset designed specifically for e-commerce MFMs. MMECInstruct comprises 75,000 samples covering 7 real-world e-commerce tasks, supporting both in-domain (IND) and out-of-domain (OOD) evaluations. Leveraging MMECInstruct, we develop CASLIE, a lightweight framework that enhances multimodal information understanding and integration for e-commerce. Our comprehensive evaluation demonstrates that MMECInstruct endows CASLIE with advanced capability and strong generalizability in e-commerce applications. MMECInstruct and CASLIE models are publicly accessible through https://github.com/ninglab/CASLIE.</abstract>
<identifier type="citekey">ling-etal-2025-captions</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.42/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>743</start>
<end>768</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data
%A Ling, Xinyi
%A Du, Hanwen
%A Peng, Bo
%A Zhu, Zhihui
%A Ning, Xia
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F ling-etal-2025-captions
%X Multimodal foundation models (MFMs) have demonstrated strong capabilities in e-commerce by effectively leveraging multimodal data to enhance product understanding and user experienceHowever, the development of e-commerce MFMs is hindered by two challenges: (1) the scarcity of large-scale, high-quality multimodal benchmark datasets; and (2) the lack of effective multimodal information integration methods in e-commerce. To address these challenges, we introduce MMECInstruct, the first large-scale, high-quality multimodal instruction dataset designed specifically for e-commerce MFMs. MMECInstruct comprises 75,000 samples covering 7 real-world e-commerce tasks, supporting both in-domain (IND) and out-of-domain (OOD) evaluations. Leveraging MMECInstruct, we develop CASLIE, a lightweight framework that enhances multimodal information understanding and integration for e-commerce. Our comprehensive evaluation demonstrates that MMECInstruct endows CASLIE with advanced capability and strong generalizability in e-commerce applications. MMECInstruct and CASLIE models are publicly accessible through https://github.com/ninglab/CASLIE.
%U https://aclanthology.org/2025.ijcnlp-long.42/
%P 743-768
Markdown (Informal)
[Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data](https://aclanthology.org/2025.ijcnlp-long.42/) (Ling et al., IJCNLP-AACL 2025)
ACL