@inproceedings{jin-etal-2026-bridging,
title = "Bridging Reasoning and Retrieval: A Large-Small Model Collaboration Framework for Multimodal Entity Alignment",
author = "Jin, Xiongnan and
Lin, Jianming and
Mei, Tiantian and
Zhu, Tiantian and
Huang, Changxin and
Chen, Jinpeng and
Hong, Chaoqun and
Li, Jianqiang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.202/",
pages = "4262--4272",
ISBN = "979-8-89176-462-0",
abstract = "Multimodal Knowledge Graphs (MMKGs) provide structured multimodal grounding for Multimodal Large Language Models (MLLMs), while Multimodal Entity Alignment (MMEA) is essential for integrating heterogeneous MMKGs. However, existing MMEA methods remain vulnerable to noisy modalities and unreliable pseudo-supervision. We propose CRMEA, a large{--}small collaborative framework for unsupervised MMEA that unifies PTM-based retrieval and MLLM-based reasoning through a closed-loop optimization process. CRMEA introduces a text-centric adaptive cross-modal coordination mechanism to regulate noisy visual evidence, together with a retrieve-and-vote strategy for reliable pseudo-supervision. Extensive experiments show that CRMEA consistently outperforms existing unsupervised MMEA methods and achieves performance competitive with state-of-the-art supervised approaches, while maintaining strong robustness, adaptability across heterogeneous backbones, and substantially improved cost-effectiveness over exhaustive MLLM-based alignment. Code and data are available at https://github.com/nsai-szu/CRMEA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2026-bridging">
<titleInfo>
<title>Bridging Reasoning and Retrieval: A Large-Small Model Collaboration Framework for Multimodal Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiongnan</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianming</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiantian</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiantian</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changxin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaoqun</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianqiang</namePart>
<namePart type="family">Li</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multimodal Knowledge Graphs (MMKGs) provide structured multimodal grounding for Multimodal Large Language Models (MLLMs), while Multimodal Entity Alignment (MMEA) is essential for integrating heterogeneous MMKGs. However, existing MMEA methods remain vulnerable to noisy modalities and unreliable pseudo-supervision. We propose CRMEA, a large–small collaborative framework for unsupervised MMEA that unifies PTM-based retrieval and MLLM-based reasoning through a closed-loop optimization process. CRMEA introduces a text-centric adaptive cross-modal coordination mechanism to regulate noisy visual evidence, together with a retrieve-and-vote strategy for reliable pseudo-supervision. Extensive experiments show that CRMEA consistently outperforms existing unsupervised MMEA methods and achieves performance competitive with state-of-the-art supervised approaches, while maintaining strong robustness, adaptability across heterogeneous backbones, and substantially improved cost-effectiveness over exhaustive MLLM-based alignment. Code and data are available at https://github.com/nsai-szu/CRMEA.</abstract>
<identifier type="citekey">jin-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.202/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4262</start>
<end>4272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging Reasoning and Retrieval: A Large-Small Model Collaboration Framework for Multimodal Entity Alignment
%A Jin, Xiongnan
%A Lin, Jianming
%A Mei, Tiantian
%A Zhu, Tiantian
%A Huang, Changxin
%A Chen, Jinpeng
%A Hong, Chaoqun
%A Li, Jianqiang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F jin-etal-2026-bridging
%X Multimodal Knowledge Graphs (MMKGs) provide structured multimodal grounding for Multimodal Large Language Models (MLLMs), while Multimodal Entity Alignment (MMEA) is essential for integrating heterogeneous MMKGs. However, existing MMEA methods remain vulnerable to noisy modalities and unreliable pseudo-supervision. We propose CRMEA, a large–small collaborative framework for unsupervised MMEA that unifies PTM-based retrieval and MLLM-based reasoning through a closed-loop optimization process. CRMEA introduces a text-centric adaptive cross-modal coordination mechanism to regulate noisy visual evidence, together with a retrieve-and-vote strategy for reliable pseudo-supervision. Extensive experiments show that CRMEA consistently outperforms existing unsupervised MMEA methods and achieves performance competitive with state-of-the-art supervised approaches, while maintaining strong robustness, adaptability across heterogeneous backbones, and substantially improved cost-effectiveness over exhaustive MLLM-based alignment. Code and data are available at https://github.com/nsai-szu/CRMEA.
%U https://aclanthology.org/2026.findings-emnlp.202/
%P 4262-4272
Markdown (Informal)
[Bridging Reasoning and Retrieval: A Large-Small Model Collaboration Framework for Multimodal Entity Alignment](https://aclanthology.org/2026.findings-emnlp.202/) (Jin et al., Findings 2026)
ACL
- Xiongnan Jin, Jianming Lin, Tiantian Mei, Tiantian Zhu, Changxin Huang, Jinpeng Chen, Chaoqun Hong, and Jianqiang Li. 2026. Bridging Reasoning and Retrieval: A Large-Small Model Collaboration Framework for Multimodal Entity Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 4262–4272, Budapest, Hungary. Association for Computational Linguistics.